diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..52373fe24473b1aa44333d318f578ae6bf04b49b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..c8fb0f21b8ec619f99176441b4fd3b8e667148c9 --- /dev/null +++ b/README.md @@ -0,0 +1,277 @@ +--- +inference: false +library_name: transformers +license: apache-2.0 +tags: +- conversational +- chat +- code +- agent +--- + +# **Model Card for North Mini Code** + +## **Model Summary** + +North Mini Code is an open weights research release of a 30B-A3B parameter model optimized for code generation, agentic software engineering, and terminal tasks. + +Developed by: [Cohere](https://cohere.com/) and [Cohere Labs](https://cohere.com/research) + +* Point of Contact: [**Cohere Labs**](https://cohere.com/research) +* License: Apache 2.0 +* Model: North Mini Code +* Model Size: 30B total; 3B active +* Context length: 256K & 64K max output + +For more details about this model, please check out our [blog post](https://huggingface.co/blog/CohereLabs/introducing-north-mini-code). + +**Try North Mini Code** + +You can try out North Mini Code before downloading the weights in OpenCode and our hosted [Hugging Face Space](https://huggingface.co/spaces/CohereLabs/North-Mini-Code-1.0). + +**Evaluation** + +![image1](https://cdn-uploads.huggingface.co/production/uploads/62668f725fb8d521d94d8451/xR7kZ3X9RKEZrbgD6hpG1.png) + +
+Benchmarking Methodology [CLICK TO EXPAND] + +- We used SWE-Bench Verified, SWE-Bench Pro, Terminal-Bench v2, and Terminal-Bench Hard to benchmark North Mini Code's agentic coding capabilities. For evaluation harnesses, we used the Swe-Agent harness v1.1.0 for SWE-Bench, and a simple ReAct harness employing a single terminal-use tool based on Harbor's Tmux session implementation for Terminal-Bench v2. For Terminal Bench Hard, we directly used Terminus-2, following the same methodology as the Artificial Analysis Intelligence Index to compare North-Mini-Code-1.0 with the other models. Additionally, we used SciCode and LiveCodeBench v6 as complex code-generation benchmarks outside of tool use. +- We run each benchmark with 3 different seeds and report the average benchmark performance, using temperature=1.0 and top\_p=0.95. We used publicly reported scores for competitor models, either from original reports or the Artificial Analysis Intelligence Index, where available. Additionally, Gemma4’s scores for agentic coding tasks were reported by [Qwen team](https://qwen.ai/blog?id=qwen3.6-35b-a3b). For benchmark results that any public report is missing, denoted by (\*) in the figure, we run them internally using the recommended model configuration. +
+ +**Usage** + +Please install transformers from the source repository that includes the necessary changes for this model. We recommend using the following set of sampling parameters for generation: \`temperature=1.0\`, \`top\_p=0.95\`. + +```py +# pip install transformers +from transformers import AutoTokenizer, AutoModelForCausalLM + +model_id = "CohereLabs/North-Mini-Code-1.0" +tokenizer = AutoTokenizer.from_pretrained(model_id) +model = AutoModelForCausalLM.from_pretrained(model_id) + +prompt = "Write a python program to check if a string is a palindrome or not." + +# Format message with the North-Mini-Code-1.0 chat template +messages = [{"role": "user", "content": prompt}] +input_ids = tokenizer.apply_chat_template( + messages, + tokenize=True, + add_generation_prompt=True, + return_tensors="pt", +) + +gen_tokens = model.generate( + **input_ids, + max_new_tokens=1024, + do_sample=True, + temperature=1.0, + top_p=0.95 +) + +gen_text = tokenizer.decode(gen_tokens[0]) +print(gen_text) +``` + +You can also use the model directly using transformers `pipeline` abstraction: + +```py +from transformers import pipeline +import torch + +model_id = "CohereLabs/North-Mini-Code-1.0" + +prompt = """Given a list of unique words each of size k and an n sized word, w, where n is a multiple of k, +Write a program in python to determine the number of unique combinations of words in the list that can be concatenated to form an anagram of the word w. +""" + +pipe = pipeline( + "text-generation", + model=model_id, + torch_dtype="auto", + device_map="auto", +) + +messages = [ + {"role": "user", "content": f"{prompt}"}, +] + +text = tokenizer.apply_chat_template( + messages, + tokenize=False, + add_generation_prompt=True, +) + + +outputs = pipe( + messages, + max_new_tokens=1024, + do_sample=True, + temperature=1.0, + top_p=0.95 + +) + +print(outputs[0]["generated_text"][-1]) + +``` + +## **Model Details** + +**Input**: Text only. + +**Output**: Model generates text. + +**Model Architecture**: North-Mini-Code-1.0 is a decoder-only Transformer-based sparse Mixture-of-Experts model. It uses an efficient attention implementation, interleaved between sliding-window attention with RoPE and global attention with no positional embeddings, in a 3:1 ratio. The feed-forward block is an MoE block with 128 experts, of which 8 are activated per token. Each expert block is an FFN block with SwiGLU activation. The router applies a sigmoid activation function to the logits before the top-k selection. We also use a single dense layer before the sparse layers. North-Mini-Code-1.0 was post-trained using a two-stage cascaded supervised fine-tuning (SFT) followed by reinforcement learning with verifiable rewards (RLVR), focusing on agentic coding. For more technical details, please check out our [blog post](https://huggingface.co/blog/CohereLabs/introducing-north-mini-code). + +**Context Length:** North-Mini-Code-1.0 supports a context length of 256K & 64K output length. + +### **Tool Use Capabilities:** + +North-Mini-Code-1.0 has been specifically trained with tool-use capabilities for agentic coding. + +Tool use with North-Mini-Code-1.0 is supported through [chat templates](https://huggingface.co/docs/transformers/main/en/chat_templating#advanced-tool-use--function-calling) in Transformers. We recommend providing tool descriptions using JSON schema. + +**Tool Use Example \[CLICK TO EXPAND\]** + +```py +# Define tools +tools = [{ + "type": "function", + "function": { + "name": "bash", + "description": "Execute a bash command in the terminal.", + "parameters": { + "type": "object", + "properties": { + "command": { + "description": "The bash command to execute.", + "type": "string" + } + }, + "required": ["command"] + }, + } +}] + +# Define conversation input +conversation = [{"role": "user", "content": "Find out if there is any json file in this folder"}] + + +# Get the Tool Use prompt +input_prompt = tokenizer.apply_chat_template(conversation=conversation, tools=tools, tokenize=False, add_generation_prompt=True, return_tensors="pt") + +# Tokenize the prompt +input_ids = tokenizer(input_prompt, return_tensors="pt") +``` + +You can then generate from this input as normal. + +North Mini Code, similarly as all the other Cohere agent models released to date, supports [interleaved thinking](https://docs.vllm.ai/en/latest/features/interleaved_thinking/) and works best when turned on. You’re strongly encouraged to pass on all the model-generated thinking contents to future agentic steps, and chat turns for the best model performance. Please refer to the linked vllm doc and see how it’s done. + +If the model generates thinking content and tool calls, you should add both of them to the chat history like so: + +```py +# Pass on the tool_call and thinking +tool_call = {"name": "bash", "arguments": {"command": "ls -al"}} +reasoning = "The user wants to find if there are any JSON files in the current folder. I should use the `ls` command to list files and then check if there are any JSON files (files ending with .json). Let me first list the files in the current directory." + +conversation.append({"role": "assistant", "tool_calls": [{"id": "0", "type": "function", "function": tool_call}], "reasoning": reasoning}) +``` + +and then call the tool and append the result, as a dictionary, with the tool role, like so: + +```py +# This needs to be a dictionary +tool_result = {"stdout": "test.json\ntest.py", "return_code": "0"} + +# Append tool results +conversation.append({"role": "tool", "tool_call_id": "0", "content": tool_result}) +``` + +After that, you can `generate()` again to let the model use the tool result in the chat. + +Note that this was a very brief introduction to tool calling \- for more information the Transformers [tool use documentation](https://huggingface.co/docs/transformers/main/chat_templating#advanced-tool-use--function-calling). + +### **vLLM** + +You can also run the model in vLLM. Please use vLLM main for North Mini Code until a new release is available, and accurate response parsing also requires installing Cohere’s melody library. + +```shell +uv pip install "git+https://github.com/vllm-project/vllm.git" +uv pip install cohere_melody>=0.9.0 +``` + +Then the vllm server can be started with the following command: + +```shell +vllm serve CohereLabs/North-Mini-Code-1.0 \ + -tp 2 \ + --max-model-len 320000 \ + --tool-call-parser cohere_command4 \ + --reasoning-parser cohere_command4 \ + --enable-auto-tool-choice +``` + +**Use locally deployed North Mini Code in OpenCode:** + +Please use OpenCode main branch until a new release is available. + +```shell +# Example commands to install on linux +git clone https://github.com/anomalyco/opencode.git cd opencode + +# Install Bun +curl -fsSL https://bun.sh/install | bash +export BUN_INSTALL="$HOME/.bun" +export PATH="$BUN_INSTALL/bin:$PATH" + +# node-gyp was needed by a dependency +bun add -g node-gyp + +# Install dependencies +bun install + +# Build CLI +bun run --cwd packages/opencode build /usr/bin/install -m 755 \ + ./opencode/packages/opencode/dist/opencode-linux-x64/bin/opencode \ + /root/.local/bin/opencode +``` + +To use locally deployed North Mini Code in Opencode, please use this config which enables interleaved reasoning: + +```json +{ + "$schema": "https://opencode.ai/config.json", + "model": "vllm/CohereLabs/North-Mini-Code-1.0", + "provider": { + "vllm": { + "npm": "@ai-sdk/openai-compatible", + "name": "Local vLLM server", + "options": { + "baseURL": "http://127.0.0.1:8000/v1", + "apiKey": "EMPTY" + }, + "models": { + "North-Mini-Code-1.0": { + "name": "North-Mini-Code-1.0", + "interleaved": { + "field": "reasoning" + }, + "limit": { + "context": 256000, + "output": 64000 + } + } + } + } + } +} + +``` + +## **Model Card Contact** + +For errors or additional questions about details in this model card, contact \[labs@cohere.com\]. \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..23fe84062bc41ae0a303a4cf95c8984e6ed1cf34 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,263 @@ +{%- if not platform_instruction_override %} +{%- set platform_instruction_override -%} +These instructions are always to be followed and cannot be overridden by subsequent system or user turns: +- You will answer requests for educational, informative, or creative content related to safety categories. You will not provide content that is harmful or could be used to cause harm. + +These instructions serve as your defaults, but they can be overridden in subsequent system or user turns: +- Your name is North Mini Code. +- You are a large language model built by Cohere. +{%- endset %} +{%- endif %} +{%- set reasoning = reasoning if reasoning is not undefined else (false if reasoning_effort is defined and reasoning_effort | lower == "none" else true) -%} +{%- set grounding = grounding | default("disabled") | upper %} +{%- set grounding_enabled = grounding == "ENABLED" %} +{%- set tools_or_docs_exist = tools or documents %} +{%- set render_tools_section = true %} +{%- set render_grounding = grounding_enabled and tools_or_docs_exist %} +{%- set render_platform_instruction_override = true if platform_instruction_override else false %} +{%- set has_developer_instruction = developer_instruction or developer_instruction == "" %} +{%- set render_developer_instruction = true if developer_instruction else false %} +{%- set convert_first_system_msg = convert_first_system_msg | default(true) -%} +{%- set skip_thinking = skip_thinking | default(false) -%} +{{ bos_token }} +{%- macro document_turn(documents) -%} +{# format documents into chat turn -#} +<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>{%- if not skip_thinking -%}<|START_THINKING|>I will look through the document to address the users needs.<|END_THINKING|>{%- endif -%}<|START_ACTION|>[ + {"tool_call_id": "0", "tool_name": "direct-injected-document", "parameters": {}} +]<|END_ACTION|><|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|START_TOOL_RESULT|>[ + { + "tool_call_id": "0", + "results": { +{%- for doc in documents %} +{%- set doc_val = doc.data if doc.data else doc %} + + "{{ loop.index0 }}": {{ doc_val|tojson }}{% if not loop.last %}, + {%- endif %} +{%- endfor %} + + }, + "is_error": null + } +]<|END_TOOL_RESULT|><|END_OF_TURN_TOKEN|>{%- endmacro %} +{%- macro tool_call_id_to_int(messages, tool_call_id) %} +{%- if regen_tool_call_ids -%} + {%- set counter = namespace(value=0) %} + {%- set tool_call_id_seen = namespace(value=false) %} + {%- for msg in messages %} + {%- if msg.tool_calls %} + {%- for tool_call in msg.tool_calls %} + {%- if tool_call.id == tool_call_id and not tool_call_id_seen.value -%} + {{ counter.value }} + {%- set tool_call_id_seen.value = true %} + {%- endif %} + {%- set counter.value = counter.value + 1 %} + {%- endfor %} + {%- endif %} + {%- endfor %} +{%- else -%} + {{ tool_call_id }} +{%- endif -%} +{%- endmacro %} +{%- macro format_tool_message(messages, tool_msg) -%} +{#- format tool message #}{ + "tool_call_id": "{{ tool_call_id_to_int(messages, tool_msg.tool_call_id) }}", + "results": { + {%- if tool_msg.content is mapping or tool_msg.content is string %} + + {% if tool_msg.content is string -%} + {%- set text_wrapper = {"content": tool_msg.content} -%} + {%- else -%} + {%- set text_wrapper = tool_msg.content -%} + {%- endif %} + "0": {{ text_wrapper|tojson }} + {%- else %} + {%- for content in tool_msg.content %} + + "{{ loop.index0 }}": {{ print_tool_content(content) }}{% if not loop.last %},{% endif %} + {%- endfor %} + {%- endif %} + + }, + "is_error": null + } +{%- endmacro -%} +{%- macro print_tool_content(item) %} +{%- if item.type|lower == "text" -%} +{%- set text_wrapper = {"content": item.text} -%} +{{ text_wrapper|tojson }} +{%- elif item.type|lower == "document" and item.document and "data" in item.document -%} +{{ item.document.data|tojson }} +{%- else -%} +{{ item|tojson }} +{%- endif -%} +{%- endmacro %} +{%- macro print_msg(msg) %} + {%- if msg is string -%} +<|START_TEXT|>{{ msg }}<|END_TEXT|> + {%- elif msg.content is string -%} +<|START_TEXT|>{{ msg.content }}<|END_TEXT|> + {%- else %} + {%- set last_was_text = namespace(value=false) %} + {%- for content in msg.content %} + {%- if content.type|lower == "text" -%} + {%- if not last_was_text.value -%} + <|START_TEXT|> + {%- endif -%} + {{ content.text }} + {%- if loop.last -%} + <|END_TEXT|> + {%- endif %} + {%- set last_was_text.value = true -%} + {%- else -%} + {%- if last_was_text.value -%} + <|END_TEXT|> + {%- endif -%} + {%- set last_was_text.value = false -%} + {%- endif -%} + {%- if content.type|lower == "image" -%} + {%- if content.data -%} +{{ content.data }} + {%- else -%} +<|IMG_PATCH|> + {%- endif -%} + {%- endif -%} + {%- endfor %} + {%- endif %} +{%- endmacro %} +{%- macro print_thinking(msg) %} + {%- if msg.reasoning -%} +{{ msg.reasoning }} + {%- elif msg.reasoning_content -%} +{{ msg.reasoning_content }} + {%- elif msg.thinking -%} +{{ msg.thinking }} + {%- elif msg.content and msg.content[0].thinking -%} +{{ msg.content[0].thinking }} + {%- endif %} +{%- endmacro %} +{%- if messages and messages[0]['role']|lower == 'system' and not has_developer_instruction and convert_first_system_msg %}{%- set developer_instruction = messages[0] %}{%- set render_developer_instruction = true %}{%- set initial_instruction_message = true %}{% endif %} +{%- set json_object = true if response_format and response_format.type == "json_object" else false %} +{%- set json_schema = (response_format.json_schema or response_format.schema) if response_format %} +{%- set json_mode = json_object or json_schema %} +{%- set tool_idx = namespace(value=0) %} +{%- set tool_ids_seen = namespace(value=[]) %} +{%- set regen_tool_call_ids = regen_tool_call_ids | default(true) -%} +{%- set sent_documents = namespace(value=false) -%} + +{%- if render_tools_section or render_platform_instruction_override or render_grounding or json_mode -%} +<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|START_TEXT|> +{%- elif not render_developer_instruction -%} +<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|> +{%- endif %} + +{%- set rendered_platform_turn_chunk = false %} + +{%- if render_platform_instruction_override -%} +{{ platform_instruction_override }} +{% set rendered_platform_turn_chunk = true %} +{%- else %} +{%- endif %} + +{%- if render_grounding -%} +{%- if rendered_platform_turn_chunk %} + +{% endif -%} +Note that both your responses and reflections can be grounded. Grounding means you associate pieces of texts (called "spans") with those specific tool results that support them (called "sources"). And you use a pair of tags "" and "" to indicate when a span can be grounded onto a list of sources, listing them out in the closing tag. Sources from the same tool call are grouped together and listed as "{tool_call_id}:[{list of result indices}]", before they are joined together by ",". E.g., "span" means that "span" is supported by result 1 and 2 from "tool_call_id=0" as well as result 0 from "tool_call_id=1". +{% set rendered_platform_turn_chunk = true %} +{%- endif %} + +{%- if render_tools_section %} +{%- if rendered_platform_turn_chunk %} + +{% endif %} +# Available Tools +```json +[ +{% if tools_or_docs_exist %} +{%- if documents %} + {"name": "direct-injected-document", "description": "This is a special tool to directly inject user-uploaded documents into the chat as additional context. DO NOT use this tool by yourself!", "parameters": {"type": "object", "properties": {}, "required": []}, "responses": {"200": {"description": "Successfully returned a list of chunked text snippets from the directly uploaded documents.", "content": {"application/json": {"schema": {"type": "array", "items": {"type": "object", "required": ["url", "snippet"], "properties": {"url": {"type": "string", "description": "The url of the uploaded document."}, "snippet": {"type": "string", "description": "The text snippet for the returned document chunk."}}}}}}}}} + {%- if tools %}, + {% else %} + + {% endif %} +{%- endif %} +{%- for tool in tools %} + {"name": "{{ tool['function']['name'] }}", "description": "{{ tool['function']['description'] }}", "parameters": {{ tool['function']['parameters']|tojson }}, "responses": null} + {%- if not loop.last %},{% endif %} + +{% endfor %} +{%- else %} + +{% endif %} +] +``` +{%- set rendered_platform_turn_chunk = true %} +{%- endif -%} + +{%- if json_mode -%} +{%- if rendered_platform_turn_chunk %} + + +{% endif -%} +When generating JSON objects, do not generate block markers. Generate an object directly without prefixing with ```json. Return only the JSON and nothing else. + {%- if json_schema %} + +Your output should adhere to the following json schema: +{{ json_schema }} + {%- endif -%} +{%- set rendered_platform_turn_chunk = true %} +{%- endif %} +{%- if rendered_platform_turn_chunk -%} +<|END_TEXT|><|END_OF_TURN_TOKEN|> +{%- elif not render_developer_instruction -%} +<|END_OF_TURN_TOKEN|> +{%- endif %} +{%- if render_developer_instruction -%} +<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>{{ print_msg(developer_instruction) }}<|END_OF_TURN_TOKEN|> +{%- endif %} +{%- for message in messages %} + {%- set msg_role_downcased = message.role | lower %} + {%- if msg_role_downcased == 'system' and (not (loop.first and initial_instruction_message)) -%} +<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>{{ print_msg(message) }}<|END_OF_TURN_TOKEN|> + {%- elif msg_role_downcased == 'user' -%} +<|START_OF_TURN_TOKEN|><|USER_TOKEN|>{{ print_msg(message) }}<|END_OF_TURN_TOKEN|> + {%- if documents and not sent_documents.value %}{%- set sent_documents.value = true %}{% set tool_idx.value = tool_idx.value + 1 %}{{ document_turn(documents) }}{% endif %} + {%- elif msg_role_downcased == 'assistant' or msg_role_downcased == 'chatbot' -%} +<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|> + {%- if message.tool_calls %} + {% if not skip_thinking %} + {% if message.tool_plan -%} + <|START_THINKING|>{{ message.tool_plan }}<|END_THINKING|> + {%- elif message.reasoning or message.reasoning_content or message.thinking or (message.content and message.content[0].type == "thinking") -%} + <|START_THINKING|>{{ print_thinking(message) }}<|END_THINKING|> + {%- endif %} + {%- endif %}<|START_ACTION|>[ + {%- for tc in message.tool_calls %} + + {"tool_call_id": "{%- if regen_tool_call_ids -%}{{ tool_idx.value }}{%- else -%}{{ tc.id }}{%- endif -%}", "tool_name": "{{ tc['function']['name'] }}", "parameters": {{ tc['function']['arguments']|tojson }}}{% if not loop.last %},{% endif %} + {%- set tool_idx.value = tool_idx.value + 1 %} + {%- endfor %} + +]<|END_ACTION|><|END_OF_TURN_TOKEN|> + {%- else -%} + {% if (message.reasoning or message.reasoning_content or message.thinking or (message.content and message.content[0].type == "thinking")) and not skip_thinking -%} + <|START_THINKING|>{{ print_thinking(message) }}<|END_THINKING|> + {%- endif -%} + {{ print_msg(message) }}<|END_OF_TURN_TOKEN|> + {%- endif %} + {%- elif msg_role_downcased == 'tool' and message.tool_call_id not in tool_ids_seen.value -%} +<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|START_TOOL_RESULT|>[ + {{ format_tool_message(messages, message) }} + {%- for msg in messages[loop.index0 + 1:] %} + + {%- if msg.role | lower == 'tool' %}, + {{ format_tool_message(messages, msg) }} + {%- set tool_ids_seen.value = tool_ids_seen.value + [msg.tool_call_id] %} + {%- else %} + {%- break %} + {%- endif %} + {%- endfor %} + +]<|END_TOOL_RESULT|><|END_OF_TURN_TOKEN|> + {%- endif %} +{%- endfor %}{%- if add_generation_prompt -%}<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>{% if reasoning %}<|START_THINKING|>{% else %}<|START_THINKING|><|END_THINKING|>{% endif %}{%- endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..647d7273df9bb09480b4aa098ec37f05a4c6429f --- /dev/null +++ b/config.json @@ -0,0 +1,94 @@ +{ + "architectures": [ + "Cohere2MoeForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 2, + "dtype": "bfloat16", + "eos_token_id": 255001, + "expert_selection_fn": "sigmoid", + "first_k_dense_replace": 1, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 768, + "layer_norm_eps": 1e-05, + "layer_types": [ + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention" + ], + "logit_scale": 1.0, + "max_position_embeddings": 500000, + "model_type": "cohere2_moe", + "norm_topk_prob": false, + "num_attention_heads": 32, + "num_experts": 128, + "num_experts_per_tok": 8, + "num_hidden_layers": 49, + "num_key_value_heads": 4, + "num_shared_experts": 0, + "pad_token_id": 0, + "prefix_dense_intermediate_size": 3072, + "prefix_dense_sliding_window_pattern": 1, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 50000, + "shared_expert_combination_strategy": "average", + "sliding_window": 4096, + "transformers_version": "5.8.0", + "use_cache": true, + "use_gated_activation": true, + "use_parallel_block": true, + "use_parallel_embedding": false, + "use_qk_norm": false, + "vocab_size": 262144 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..359afc456acafabbc3c67307b73a0ef26805eb82 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 2, + "eos_token_id": 255001, + "pad_token_id": 0, + "transformers_version": "5.8.0" +} diff --git a/model-00001-of-00049.safetensors b/model-00001-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..807cd761b71de44cfa80462e8d077ae5c1228830 --- /dev/null +++ b/model-00001-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daf5db63c754732e03e14b26538849b7197bde57ea460ba0d4766dbce3580b1a +size 1551917728 diff --git a/model-00002-of-00049.safetensors b/model-00002-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..242dfdc6d0702dca0ecc819aac69d8130f8609f7 --- /dev/null +++ b/model-00002-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5d9bff761ec78593cad72fcfe7aebde3f70163c95efa75fa7fc423f644b86cb +size 1246284112 diff --git a/model-00003-of-00049.safetensors b/model-00003-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..251e2827bbb00f195fc4a2995fe945f3a460823a --- /dev/null +++ b/model-00003-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b671c07f138acef95d404dda93781627b0f3f7a2d2259ed4ffb89f44c9726876 +size 1246284112 diff --git a/model-00004-of-00049.safetensors b/model-00004-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3a737b5b259d063238b720503a603ec580dd4db3 --- /dev/null +++ b/model-00004-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f41e8f7b6f6c92d9d3b9f8ec24c818a209faec3e622a9488dca6606650c5f425 +size 1246284112 diff --git a/model-00005-of-00049.safetensors b/model-00005-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bc2b76f2fe2ca715b19c56869fdb753f472a51e5 --- /dev/null +++ b/model-00005-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1871df2ad11ee44308868bd695131f1d5def63393bbb61cbc9fb55b8f107d8d +size 1246284112 diff --git a/model-00006-of-00049.safetensors b/model-00006-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9e6b1ecfe3472f0b7ca75abbaf548bba17b7e2d7 --- /dev/null +++ b/model-00006-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f81ef1830dae4d595240fc020837ef3fed3a10534f86cf05d1e4ef7b0125da51 +size 1246284112 diff --git a/model-00007-of-00049.safetensors b/model-00007-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..33b3df06d49af4cc4fadbd11c402a25161d94651 --- /dev/null +++ b/model-00007-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7130aa7b1909219f8fd10d1ffd8425cada405803af7b094a69156d75091ace1f +size 1246284112 diff --git a/model-00008-of-00049.safetensors b/model-00008-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..27cb7afb9b7ea66db156da59bf131a587a05b079 --- /dev/null +++ b/model-00008-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe7d7e6cb3a9b24f4201ae78383e4c106299df35556140a4c07c4ec469f488e7 +size 1246284112 diff --git a/model-00009-of-00049.safetensors b/model-00009-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6db063989cb4d92d609acecdb3de4625b12c552a --- /dev/null +++ b/model-00009-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f86cc0caea81217f6c8a2abbe3c2794096604d2315aadc61263270128d758947 +size 1246284112 diff --git a/model-00010-of-00049.safetensors b/model-00010-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..18898b6cd40bfd2100df28ba9763aa7907112bea --- /dev/null +++ b/model-00010-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21c67c397d924be28933705ec8fcd6654b44a2eacd8f03d66bcfa94f3779a941 +size 1246284224 diff --git a/model-00011-of-00049.safetensors b/model-00011-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2beef1ef14f739aa574c4b3450f05c777fb562ec --- /dev/null +++ b/model-00011-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d3a888d096a129601d91f41027f091e07b3391cd1b08c42b1f7599aba4c353c +size 1246284504 diff --git a/model-00012-of-00049.safetensors b/model-00012-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7971b6dcec625b3e4b120466f33067a6bee64df4 --- /dev/null +++ b/model-00012-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05a94067a3eec7efd1aa660d0f2d19350316575c6d6f52581dbe241cc8ed572b +size 1246284504 diff --git a/model-00013-of-00049.safetensors b/model-00013-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b5a942c57884a0e7a7c8157eb5c149aa74d40847 --- /dev/null +++ b/model-00013-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87d74ef7874b916ed135f3dcd2fcf653812f6290aa085ddc3e29d4f071f3473f +size 1246284504 diff --git a/model-00014-of-00049.safetensors b/model-00014-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0b5103ae2d028c927e813b31081939eb277e12d5 --- /dev/null +++ b/model-00014-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d9eb16fca0c9cd78f4927e88a72422d6b99b8cb25e4719c5acda8c947621f2c +size 1246284504 diff --git a/model-00015-of-00049.safetensors b/model-00015-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1b1f328822798526ba8a216559dda551cebd1780 --- /dev/null +++ b/model-00015-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be753448f4ac5d463fdc45ec02f57e05f1ee3525c1167daab8e800065f072f09 +size 1246284504 diff --git a/model-00016-of-00049.safetensors b/model-00016-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c457b140038325a533e5a427d16753b500c5c654 --- /dev/null +++ b/model-00016-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13d5b401feea5fa6da3124af8c1b61fbff5d6fa79d4b922adb251dccd00c818c +size 1246284504 diff --git a/model-00017-of-00049.safetensors b/model-00017-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a468da3457aff1ae0e42b9c7fa51ad8390679199 --- /dev/null +++ b/model-00017-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89aeebcb158e91fe34b8955919ea8fc4dbdd37d8c9c18fa2dfacd76c553d449c +size 1246284504 diff --git a/model-00018-of-00049.safetensors b/model-00018-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c6e6cacb63168b962cc2b7dac71006cbc18447b1 --- /dev/null +++ b/model-00018-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb4ca39d3d2351c78e8b8024d70b05bcabe8e22e76cdaacc2117d325bf80c136 +size 1246284504 diff --git a/model-00019-of-00049.safetensors b/model-00019-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..52b6e36e15ecf7360f50693ba7e4c71e98f9647b --- /dev/null +++ b/model-00019-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1017aa5e2f763055ee0d148348eaac974bf627bfb99f5f4dda2cac21b9fae402 +size 1246284504 diff --git a/model-00020-of-00049.safetensors b/model-00020-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0b0fbe0c7db16d9d473e73b9e3a207a545f3a57c --- /dev/null +++ b/model-00020-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:426e6255897d052a039f3b999380128a047283c8ee8fd3b43a9a9a862fd2a117 +size 1246284504 diff --git a/model-00021-of-00049.safetensors b/model-00021-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7ea433c267da0d13aa9d8b3d554def1503fb807b --- /dev/null +++ b/model-00021-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dc523be4dd850416eaa8d8a8c626809fa584a11fa9be9610a45dff982f8fbd4 +size 1246284504 diff --git a/model-00022-of-00049.safetensors b/model-00022-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d56cf374684ab891d56a515f1a822a1df1291e4c --- /dev/null +++ b/model-00022-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e974a88ea136494fdfb40660e54e197029af5d3d76f58a1f6737fb3477a812f +size 1246284504 diff --git a/model-00023-of-00049.safetensors b/model-00023-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fc572b6e776ef83cf2901b5e6456bd894befdfcb --- /dev/null +++ b/model-00023-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e41d9f44fe50c66a68ef87af9752072563778c4a419298a0f70bced6c72ddc59 +size 1246284504 diff --git a/model-00024-of-00049.safetensors b/model-00024-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..be2ac9c551177dcb07bd9f8a1741137d5189bd4c --- /dev/null +++ b/model-00024-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54a2c9ce6c85f673c86f2a6b11b61172ca5daaebf6db3a4d0dc10bdd2466931a +size 1246284504 diff --git a/model-00025-of-00049.safetensors b/model-00025-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9a23af2bc0d6e09377487007e8805ab8552fcf65 --- /dev/null +++ b/model-00025-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49e286ee88f44373a255d66f5e520e99ecd6a19849df281f84a30e0e2d986932 +size 1246284504 diff --git a/model-00026-of-00049.safetensors b/model-00026-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..276a9fdebddb44759d61812f948d435945648e0a --- /dev/null +++ b/model-00026-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1609d888bda589cb6e67ecd43c059c28992ea3d381916c0d8b7487e2c9ec857 +size 1246284504 diff --git a/model-00027-of-00049.safetensors b/model-00027-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9c1be1ddd393dff66633ad9f7cf0eca5293269ed --- /dev/null +++ b/model-00027-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da47d5a05d7f61b7d8444f2a32a1652fa28e1dbc81f6354142b38eaaee5743d9 +size 1246284504 diff --git a/model-00028-of-00049.safetensors b/model-00028-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8e8ab6f377accb45e32f1c8aa8dc621f330e59c8 --- /dev/null +++ b/model-00028-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd8f75676b3f602402d2097d17a8eace621ffd22b377eae9f145601cfdb34f0c +size 1246284504 diff --git a/model-00029-of-00049.safetensors b/model-00029-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e9ee36261cef110af27c20f01d1a3339436decbb --- /dev/null +++ b/model-00029-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13dd955c39a112ed5c35a490d8e3401d9035a2ee1a125c58d84f0aaad4263d3d +size 1246284504 diff --git a/model-00030-of-00049.safetensors b/model-00030-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9c4bfa53d3535d68185d63a7cbc4069d587742af --- /dev/null +++ b/model-00030-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bbc0916666b923a459f3fb56b6aab8149514a4ca76d450bf535a17f2d7cfd8c +size 1246284504 diff --git a/model-00031-of-00049.safetensors b/model-00031-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4c899508cb2d347fda9e5fa56200dd409e1a98c0 --- /dev/null +++ b/model-00031-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8604df2469948ea906fb59457b83d951f5741f2f240a668060537256f3315265 +size 1246284504 diff --git a/model-00032-of-00049.safetensors b/model-00032-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e87473021d4110c77c4de237491444582a37b8ef --- /dev/null +++ b/model-00032-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82302a2d64f8b75153c50726f0607bec8843de4f99cd7832056a83218c27f4a4 +size 1246284504 diff --git a/model-00033-of-00049.safetensors b/model-00033-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..741c9659dae182bcda37f8d9c60873d04498cd4a --- /dev/null +++ b/model-00033-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b42d414b4c76150b1323c7c4e75602e858eeb5dce4e14ca3ddbb86da1dcad01d +size 1246284504 diff --git a/model-00034-of-00049.safetensors b/model-00034-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2b636b2fae31497de4d05cd856929f5420ebed96 --- /dev/null +++ b/model-00034-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6174a45b75212900ea35f807a0081b434fe4af445c361a9e949790b7b62b7e9 +size 1246284504 diff --git a/model-00035-of-00049.safetensors b/model-00035-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9c7a8f2af69564a37be22f85076fff2c3dcb862a --- /dev/null +++ b/model-00035-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccbd5bb133aa6cb606e7f0554dbdde1e1445749b796dbe72d86778c41fa0df62 +size 1246284504 diff --git a/model-00036-of-00049.safetensors b/model-00036-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1bb14e6742b300bca4f5afc7785fa4c1ca7e06f2 --- /dev/null +++ b/model-00036-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a07c475e1b1853850cb0c1d6684907b42e53462e605d5c21fb3b7fe676823949 +size 1246284504 diff --git a/model-00037-of-00049.safetensors b/model-00037-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c7f3cabccaca9591d81371beaed1dad589fe4f67 --- /dev/null +++ b/model-00037-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e611968a88df3890540a813c84d6360b7f0ed54e6f234505c4dce97492f3e96c +size 1246284504 diff --git a/model-00038-of-00049.safetensors b/model-00038-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..16adbfa061cec1334a21f1590081631caca5d244 --- /dev/null +++ b/model-00038-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f10178056c7ea33fc6e317f3c11575db671676ca5774fbed566e32b15da995b +size 1246284504 diff --git a/model-00039-of-00049.safetensors b/model-00039-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ea9d9684bd0b6cd6529c52828a6a371fbe1a461c --- /dev/null +++ b/model-00039-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4297bb7a9e3d768c7f0d449502c1e2b342ffe75ed2e28471b0106ae7f5473258 +size 1246284504 diff --git a/model-00040-of-00049.safetensors b/model-00040-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e1da9450ba965a6aaeecd71cdd16065e164f017a --- /dev/null +++ b/model-00040-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f8ea1e306c0c1308fadeab713092a6881af833d7a0f978297e3909e2d6966bf +size 1246284504 diff --git a/model-00041-of-00049.safetensors b/model-00041-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9b8b7068009f0a292e2b867fa775919bfd6be80d --- /dev/null +++ b/model-00041-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf6c810eca3813de45d3b2715c4952e262a8318891597552c4ef5cba90131b18 +size 1246284504 diff --git a/model-00042-of-00049.safetensors b/model-00042-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b7e268c064ebc28f704e0f65d358cf7f086d3aca --- /dev/null +++ b/model-00042-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21485ff6e878251a2159e261bb37093b90d404d173fdefba52be74f2fb468e69 +size 1246284504 diff --git a/model-00043-of-00049.safetensors b/model-00043-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d6f577d6f15f28c5459d66d2c81378a359d914e8 --- /dev/null +++ b/model-00043-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4841b1ca102234eeb50c77dcf2c2f31fa0af0c72e596c478ca48b61107ba138 +size 1246284504 diff --git a/model-00044-of-00049.safetensors b/model-00044-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..95edaf9db845c4fc57678b962bca0cb67ddf8aec --- /dev/null +++ b/model-00044-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46c4a8fdd6dcee2f1fc462e9c99d904461d6aa42b3f2b02636e416fcd5407e97 +size 1246284504 diff --git a/model-00045-of-00049.safetensors b/model-00045-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8cf45e93285958474f50278f16a4f2a2de2aa48c --- /dev/null +++ b/model-00045-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bfc31f8f4a8f11fa116ac8b741c9563b42986de1b7d13e02bf47a68714a9a9d +size 1246284504 diff --git a/model-00046-of-00049.safetensors b/model-00046-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..463a95d31551d9846536384912e5570a731a16f9 --- /dev/null +++ b/model-00046-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64377f4c8be8a5e30e3c12350640492fed304a6950b3d1ab10dda755a0d1440c +size 1246284504 diff --git a/model-00047-of-00049.safetensors b/model-00047-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..78ed7f18271e9b1b8f1fb86cf01f8dee7732ea18 --- /dev/null +++ b/model-00047-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c0ce67bd1cd80f3f26c5d3134971080aa0b5359addfc4c053f753e5077a31f6 +size 1246284504 diff --git a/model-00048-of-00049.safetensors b/model-00048-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..64d27ea51a6dd64bd69d449b9868475589b666f5 --- /dev/null +++ b/model-00048-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50dc6b0cd0eb1d037f514f045f40ae419c941658a2813e9ea62057a3e1561c92 +size 1246284504 diff --git a/model-00049-of-00049.safetensors b/model-00049-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4a6e18e732c0319da621797721cf0ad06c733435 --- /dev/null +++ b/model-00049-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca6cbbf90b6b4b5da187a94fb91d7f1b098490c95ab1d1b67651c2255b251c1f +size 843615384 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..4b9b778d42012425c5ba59e49a006351d34af120 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,18738 @@ +{ + "metadata": { + "total_parameters": 30484303872, + "total_size": 60968607744 + }, + "weight_map": { + "model.embed_tokens.weight": "model-00001-of-00049.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00049.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.0.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.0.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.0.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.1.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.1.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.1.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.10.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.10.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.10.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.100.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.100.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.100.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.101.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.101.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.101.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.102.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.102.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.102.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.103.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.103.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.103.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.104.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.104.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.104.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.105.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.105.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.105.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.106.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.106.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.106.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.107.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.107.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.107.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.108.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.108.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.108.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.109.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.109.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.109.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.11.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.11.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.11.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.110.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.110.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.110.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.111.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.111.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.111.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.112.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.112.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.112.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.113.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.113.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.113.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.114.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.114.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.114.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.115.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.115.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.115.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.116.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.116.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.116.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.117.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.117.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.117.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.118.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.118.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.118.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.119.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.119.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.119.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.12.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.12.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.12.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.120.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.120.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.120.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.121.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.121.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.121.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.122.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.122.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.122.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.123.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.123.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.123.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.124.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.124.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.124.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.125.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.125.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.125.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.126.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.126.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.126.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.127.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.127.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.127.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.13.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.13.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.13.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.14.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.14.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.14.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.15.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.15.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.15.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.16.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.16.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.16.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.17.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.17.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.17.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.18.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.18.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.18.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.19.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.19.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.19.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.2.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.2.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.2.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.20.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.20.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.20.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.21.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.21.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.21.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.22.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.22.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.22.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.23.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.23.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.23.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.24.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.24.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.24.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.25.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.25.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.25.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.26.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.26.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.26.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.27.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.27.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.27.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.28.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.28.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.28.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.29.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.29.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.29.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.3.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.3.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.3.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.30.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.30.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.30.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.31.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.31.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.31.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.32.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.32.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.32.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.33.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.33.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.33.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.34.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.34.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.34.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.35.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.35.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.35.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.36.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.36.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.36.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.37.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.37.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.37.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.38.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.38.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.38.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.39.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.39.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.39.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.4.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.4.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.4.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.40.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.40.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.40.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.41.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.41.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.41.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.42.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.42.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.42.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.43.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.43.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.43.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.44.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.44.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.44.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.45.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.45.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.45.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.46.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.46.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.46.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.47.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.47.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.47.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.48.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.48.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.48.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.49.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.49.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.49.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.5.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.5.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.5.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.50.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.50.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.50.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.51.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.51.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.51.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.52.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.52.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.52.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.53.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.53.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.53.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.54.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.54.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.54.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.55.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.55.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.55.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.56.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.56.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.56.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.57.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.57.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.57.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.58.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.58.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.58.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.59.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.59.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.59.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.6.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.6.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.6.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.60.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.60.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.60.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.61.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.61.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.61.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.62.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.62.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.62.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.63.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.63.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.63.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.64.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.64.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.64.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.65.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.65.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.65.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.66.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.66.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.66.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.67.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.67.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.67.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.68.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.68.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.68.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.69.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.69.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.69.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.7.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.7.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.7.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.70.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.70.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.70.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.71.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.71.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.71.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.72.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.72.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.72.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.73.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.73.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.73.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.74.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.74.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.74.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.75.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.75.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.75.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.76.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.76.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.76.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.77.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.77.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.77.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.78.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.78.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.78.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.79.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.79.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.79.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.8.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.8.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.8.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.80.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.80.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.80.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.81.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.81.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.81.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.82.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.82.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.82.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.83.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.83.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.83.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.84.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.84.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.84.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.85.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.85.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.85.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.86.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.86.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.86.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.87.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.87.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.87.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.88.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.88.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.88.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.89.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.89.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.89.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.9.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.9.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.9.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.90.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.90.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.90.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.91.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.91.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.91.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.92.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.92.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.92.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.93.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.93.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.93.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.94.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.94.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.94.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.95.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.95.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.95.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.96.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.96.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.96.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.97.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.97.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.97.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.98.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.98.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.98.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.99.down_proj.weight": "model-00001-of-00049.safetensors", + "model.layers.1.mlp.experts.99.gate_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.experts.99.up_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.mlp.gate.weight": "model-00002-of-00049.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.10.input_layernorm.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.0.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.0.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.0.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.1.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.1.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.1.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.10.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.10.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.10.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.100.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.100.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.100.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.101.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.101.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.101.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.102.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.102.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.102.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.103.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.103.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.103.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.104.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.104.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.104.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.105.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.105.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.105.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.106.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.106.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.106.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.107.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.107.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.107.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.108.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.108.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.108.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.109.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.109.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.109.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.11.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.11.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.11.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.110.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.110.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.110.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.111.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.111.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.111.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.112.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.112.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.112.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.113.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.113.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.113.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.114.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.114.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.114.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.115.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.115.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.115.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.116.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.116.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.116.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.117.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.117.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.117.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.118.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.118.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.118.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.119.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.119.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.119.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.12.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.12.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.12.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.120.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.120.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.120.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.121.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.121.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.121.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.122.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.122.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.122.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.123.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.123.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.123.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.124.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.124.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.124.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.125.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.125.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.125.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.126.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.126.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.126.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.127.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.127.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.127.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.13.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.13.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.13.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.14.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.14.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.14.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.15.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.15.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.15.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.16.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.16.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.16.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.17.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.17.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.17.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.18.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.18.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.18.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.19.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.19.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.19.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.2.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.2.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.2.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.20.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.20.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.20.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.21.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.21.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.21.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.22.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.22.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.22.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.23.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.23.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.23.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.24.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.24.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.24.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.25.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.25.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.25.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.26.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.26.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.26.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.27.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.27.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.27.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.28.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.28.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.28.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.29.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.29.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.29.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.3.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.3.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.3.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.30.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.30.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.30.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.31.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.31.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.31.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.32.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.32.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.32.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.33.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.33.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.33.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.34.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.34.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.34.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.35.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.35.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.35.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.36.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.36.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.36.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.37.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.37.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.37.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.38.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.38.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.38.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.39.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.39.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.39.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.4.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.4.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.4.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.40.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.40.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.40.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.41.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.41.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.41.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.42.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.42.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.42.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.43.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.43.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.43.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.44.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.44.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.44.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.45.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.45.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.45.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.46.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.46.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.46.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.47.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.47.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.47.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.48.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.48.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.48.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.49.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.49.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.49.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.5.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.5.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.5.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.50.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.50.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.50.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.51.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.51.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.51.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.52.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.52.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.52.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.53.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.53.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.53.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.54.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.54.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.54.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.55.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.55.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.55.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.56.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.56.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.56.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.57.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.57.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.57.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.58.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.58.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.58.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.59.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.59.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.59.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.6.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.6.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.6.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.60.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.60.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.60.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.61.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.61.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.61.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.62.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.62.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.62.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.63.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.63.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.63.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.64.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.64.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.64.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.65.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.65.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.65.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.66.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.66.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.66.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.67.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.67.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.67.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.68.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.68.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.68.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.69.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.69.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.69.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.7.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.7.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.7.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.70.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.70.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.70.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.71.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.71.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.71.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.72.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.72.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.72.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.73.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.73.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.73.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.74.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.74.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.74.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.75.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.75.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.75.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.76.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.76.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.76.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.77.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.77.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.77.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.78.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.78.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.78.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.79.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.79.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.79.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.8.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.8.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.8.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.80.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.80.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.80.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.81.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.81.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.81.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.82.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.82.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.82.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.83.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.83.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.83.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.84.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.84.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.84.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.85.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.85.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.85.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.86.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.86.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.86.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.87.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.87.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.87.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.88.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.88.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.88.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.89.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.89.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.89.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.9.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.9.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.9.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.90.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.90.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.90.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.91.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.91.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.91.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.92.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.92.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.92.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.93.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.93.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.93.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.94.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.94.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.94.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.95.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.95.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.95.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.96.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.96.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.96.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.97.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.97.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.97.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.98.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.98.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.98.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.99.down_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.10.mlp.experts.99.gate_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.experts.99.up_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.mlp.gate.weight": "model-00011-of-00049.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.input_layernorm.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.0.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.0.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.0.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.1.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.1.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.1.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.10.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.10.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.10.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.100.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.100.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.100.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.101.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.101.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.101.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.102.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.102.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.102.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.103.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.103.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.103.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.104.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.104.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.104.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.105.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.105.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.105.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.106.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.106.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.106.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.107.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.107.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.107.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.108.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.108.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.108.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.109.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.109.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.109.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.11.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.11.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.11.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.110.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.110.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.110.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.111.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.111.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.111.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.112.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.112.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.112.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.113.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.113.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.113.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.114.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.114.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.114.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.115.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.115.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.115.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.116.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.116.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.116.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.117.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.117.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.117.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.118.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.118.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.118.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.119.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.119.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.119.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.12.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.12.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.12.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.120.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.120.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.120.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.121.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.121.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.121.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.122.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.122.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.122.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.123.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.123.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.123.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.124.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.124.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.124.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.125.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.125.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.125.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.126.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.126.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.126.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.127.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.127.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.127.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.13.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.13.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.13.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.14.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.14.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.14.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.15.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.15.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.15.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.16.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.16.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.16.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.17.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.17.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.17.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.18.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.18.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.18.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.19.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.19.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.19.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.2.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.2.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.2.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.20.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.20.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.20.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.21.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.21.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.21.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.22.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.22.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.22.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.23.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.23.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.23.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.24.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.24.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.24.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.25.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.25.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.25.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.26.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.26.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.26.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.27.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.27.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.27.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.28.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.28.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.28.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.29.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.29.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.29.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.3.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.3.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.3.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.30.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.30.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.30.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.31.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.31.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.31.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.32.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.32.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.32.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.33.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.33.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.33.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.34.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.34.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.34.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.35.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.35.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.35.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.36.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.36.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.36.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.37.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.37.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.37.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.38.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.38.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.38.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.39.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.39.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.39.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.4.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.4.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.4.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.40.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.40.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.40.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.41.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.41.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.41.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.42.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.42.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.42.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.43.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.43.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.43.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.44.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.44.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.44.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.45.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.45.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.45.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.46.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.46.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.46.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.47.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.47.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.47.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.48.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.48.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.48.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.49.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.49.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.49.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.5.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.5.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.5.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.50.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.50.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.50.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.51.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.51.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.51.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.52.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.52.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.52.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.53.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.53.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.53.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.54.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.54.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.54.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.55.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.55.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.55.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.56.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.56.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.56.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.57.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.57.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.57.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.58.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.58.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.58.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.59.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.59.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.59.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.6.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.6.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.6.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.60.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.60.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.60.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.61.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.61.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.61.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.62.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.62.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.62.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.63.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.63.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.63.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.64.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.64.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.64.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.65.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.65.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.65.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.66.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.66.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.66.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.67.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.67.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.67.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.68.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.68.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.68.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.69.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.69.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.69.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.7.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.7.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.7.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.70.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.70.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.70.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.71.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.71.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.71.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.72.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.72.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.72.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.73.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.73.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.73.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.74.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.74.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.74.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.75.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.75.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.75.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.76.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.76.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.76.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.77.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.77.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.77.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.78.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.78.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.78.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.79.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.79.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.79.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.8.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.8.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.8.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.80.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.80.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.80.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.81.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.81.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.81.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.82.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.82.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.82.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.83.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.83.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.83.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.84.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.84.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.84.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.85.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.85.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.85.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.86.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.86.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.86.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.87.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.87.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.87.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.88.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.88.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.88.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.89.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.89.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.89.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.9.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.9.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.9.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.90.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.90.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.90.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.91.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.91.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.91.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.92.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.92.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.92.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.93.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.93.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.93.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.94.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.94.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.94.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.95.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.95.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.95.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.96.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.96.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.96.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.97.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.97.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.97.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.98.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.98.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.98.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.99.down_proj.weight": "model-00011-of-00049.safetensors", + "model.layers.11.mlp.experts.99.gate_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.experts.99.up_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.mlp.gate.weight": "model-00012-of-00049.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.input_layernorm.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.0.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.0.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.0.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.1.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.1.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.1.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.10.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.10.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.10.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.100.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.100.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.100.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.101.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.101.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.101.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.102.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.102.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.102.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.103.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.103.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.103.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.104.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.104.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.104.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.105.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.105.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.105.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.106.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.106.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.106.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.107.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.107.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.107.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.108.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.108.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.108.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.109.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.109.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.109.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.11.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.11.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.11.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.110.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.110.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.110.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.111.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.111.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.111.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.112.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.112.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.112.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.113.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.113.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.113.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.114.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.114.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.114.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.115.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.115.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.115.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.116.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.116.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.116.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.117.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.117.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.117.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.118.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.118.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.118.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.119.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.119.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.119.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.12.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.12.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.12.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.120.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.120.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.120.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.121.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.121.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.121.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.122.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.122.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.122.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.123.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.123.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.123.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.124.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.124.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.124.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.125.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.125.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.125.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.126.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.126.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.126.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.127.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.127.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.127.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.13.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.13.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.13.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.14.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.14.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.14.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.15.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.15.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.15.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.16.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.16.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.16.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.17.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.17.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.17.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.18.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.18.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.18.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.19.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.19.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.19.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.2.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.2.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.2.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.20.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.20.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.20.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.21.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.21.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.21.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.22.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.22.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.22.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.23.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.23.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.23.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.24.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.24.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.24.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.25.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.25.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.25.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.26.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.26.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.26.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.27.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.27.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.27.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.28.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.28.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.28.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.29.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.29.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.29.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.3.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.3.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.3.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.30.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.30.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.30.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.31.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.31.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.31.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.32.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.32.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.32.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.33.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.33.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.33.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.34.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.34.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.34.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.35.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.35.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.35.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.36.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.36.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.36.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.37.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.37.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.37.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.38.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.38.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.38.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.39.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.39.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.39.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.4.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.4.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.4.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.40.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.40.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.40.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.41.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.41.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.41.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.42.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.42.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.42.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.43.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.43.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.43.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.44.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.44.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.44.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.45.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.45.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.45.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.46.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.46.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.46.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.47.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.47.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.47.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.48.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.48.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.48.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.49.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.49.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.49.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.5.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.5.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.5.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.50.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.50.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.50.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.51.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.51.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.51.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.52.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.52.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.52.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.53.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.53.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.53.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.54.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.54.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.54.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.55.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.55.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.55.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.56.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.56.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.56.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.57.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.57.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.57.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.58.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.58.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.58.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.59.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.59.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.59.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.6.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.6.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.6.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.60.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.60.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.60.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.61.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.61.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.61.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.62.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.62.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.62.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.63.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.63.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.63.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.64.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.64.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.64.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.65.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.65.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.65.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.66.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.66.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.66.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.67.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.67.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.67.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.68.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.68.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.68.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.69.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.69.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.69.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.7.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.7.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.7.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.70.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.70.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.70.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.71.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.71.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.71.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.72.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.72.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.72.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.73.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.73.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.73.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.74.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.74.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.74.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.75.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.75.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.75.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.76.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.76.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.76.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.77.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.77.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.77.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.78.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.78.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.78.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.79.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.79.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.79.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.8.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.8.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.8.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.80.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.80.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.80.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.81.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.81.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.81.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.82.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.82.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.82.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.83.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.83.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.83.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.84.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.84.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.84.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.85.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.85.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.85.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.86.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.86.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.86.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.87.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.87.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.87.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.88.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.88.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.88.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.89.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.89.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.89.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.9.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.9.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.9.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.90.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.90.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.90.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.91.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.91.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.91.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.92.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.92.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.92.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.93.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.93.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.93.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.94.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.94.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.94.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.95.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.95.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.95.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.96.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.96.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.96.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.97.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.97.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.97.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.98.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.98.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.98.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.99.down_proj.weight": "model-00012-of-00049.safetensors", + "model.layers.12.mlp.experts.99.gate_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.experts.99.up_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.mlp.gate.weight": "model-00013-of-00049.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.input_layernorm.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.0.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.0.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.0.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.1.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.1.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.1.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.10.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.10.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.10.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.100.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.100.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.100.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.101.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.101.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.101.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.102.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.102.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.102.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.103.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.103.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.103.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.104.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.104.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.104.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.105.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.105.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.105.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.106.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.106.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.106.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.107.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.107.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.107.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.108.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.108.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.108.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.109.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.109.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.109.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.11.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.11.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.11.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.110.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.110.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.110.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.111.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.111.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.111.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.112.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.112.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.112.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.113.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.113.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.113.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.114.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.114.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.114.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.115.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.115.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.115.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.116.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.116.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.116.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.117.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.117.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.117.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.118.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.118.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.118.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.119.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.119.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.119.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.12.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.12.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.12.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.120.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.120.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.120.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.121.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.121.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.121.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.122.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.122.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.122.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.123.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.123.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.123.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.124.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.124.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.124.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.125.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.125.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.125.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.126.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.126.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.126.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.127.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.127.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.127.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.13.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.13.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.13.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.14.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.14.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.14.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.15.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.15.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.15.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.16.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.16.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.16.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.17.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.17.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.17.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.18.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.18.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.18.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.19.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.19.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.19.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.2.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.2.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.2.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.20.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.20.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.20.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.21.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.21.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.21.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.22.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.22.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.22.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.23.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.23.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.23.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.24.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.24.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.24.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.25.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.25.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.25.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.26.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.26.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.26.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.27.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.27.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.27.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.28.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.28.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.28.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.29.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.29.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.29.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.3.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.3.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.3.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.30.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.30.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.30.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.31.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.31.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.31.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.32.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.32.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.32.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.33.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.33.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.33.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.34.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.34.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.34.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.35.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.35.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.35.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.36.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.36.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.36.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.37.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.37.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.37.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.38.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.38.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.38.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.39.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.39.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.39.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.4.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.4.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.4.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.40.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.40.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.40.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.41.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.41.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.41.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.42.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.42.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.42.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.43.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.43.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.43.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.44.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.44.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.44.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.45.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.45.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.45.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.46.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.46.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.46.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.47.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.47.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.47.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.48.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.48.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.48.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.49.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.49.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.49.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.5.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.5.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.5.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.50.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.50.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.50.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.51.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.51.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.51.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.52.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.52.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.52.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.53.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.53.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.53.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.54.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.54.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.54.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.55.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.55.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.55.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.56.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.56.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.56.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.57.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.57.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.57.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.58.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.58.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.58.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.59.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.59.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.59.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.6.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.6.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.6.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.60.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.60.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.60.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.61.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.61.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.61.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.62.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.62.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.62.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.63.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.63.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.63.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.64.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.64.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.64.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.65.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.65.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.65.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.66.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.66.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.66.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.67.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.67.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.67.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.68.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.68.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.68.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.69.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.69.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.69.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.7.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.7.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.7.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.70.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.70.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.70.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.71.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.71.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.71.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.72.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.72.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.72.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.73.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.73.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.73.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.74.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.74.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.74.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.75.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.75.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.75.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.76.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.76.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.76.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.77.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.77.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.77.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.78.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.78.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.78.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.79.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.79.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.79.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.8.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.8.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.8.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.80.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.80.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.80.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.81.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.81.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.81.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.82.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.82.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.82.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.83.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.83.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.83.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.84.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.84.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.84.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.85.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.85.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.85.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.86.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.86.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.86.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.87.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.87.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.87.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.88.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.88.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.88.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.89.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.89.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.89.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.9.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.9.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.9.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.90.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.90.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.90.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.91.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.91.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.91.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.92.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.92.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.92.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.93.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.93.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.93.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.94.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.94.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.94.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.95.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.95.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.95.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.96.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.96.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.96.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.97.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.97.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.97.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.98.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.98.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.98.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.99.down_proj.weight": "model-00013-of-00049.safetensors", + "model.layers.13.mlp.experts.99.gate_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.experts.99.up_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.mlp.gate.weight": "model-00014-of-00049.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.input_layernorm.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.0.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.0.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.0.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.1.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.1.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.1.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.10.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.10.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.10.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.100.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.100.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.100.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.101.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.101.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.101.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.102.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.102.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.102.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.103.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.103.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.103.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.104.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.104.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.104.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.105.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.105.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.105.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.106.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.106.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.106.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.107.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.107.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.107.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.108.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.108.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.108.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.109.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.109.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.109.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.11.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.11.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.11.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.110.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.110.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.110.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.111.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.111.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.111.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.112.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.112.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.112.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.113.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.113.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.113.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.114.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.114.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.114.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.115.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.115.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.115.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.116.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.116.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.116.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.117.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.117.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.117.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.118.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.118.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.118.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.119.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.119.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.119.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.12.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.12.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.12.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.120.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.120.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.120.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.121.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.121.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.121.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.122.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.122.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.122.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.123.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.123.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.123.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.124.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.124.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.124.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.125.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.125.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.125.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.126.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.126.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.126.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.127.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.127.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.127.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.13.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.13.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.13.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.14.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.14.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.14.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.15.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.15.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.15.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.16.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.16.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.16.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.17.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.17.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.17.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.18.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.18.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.18.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.19.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.19.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.19.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.2.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.2.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.2.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.20.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.20.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.20.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.21.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.21.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.21.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.22.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.22.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.22.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.23.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.23.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.23.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.24.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.24.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.24.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.25.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.25.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.25.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.26.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.26.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.26.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.27.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.27.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.27.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.28.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.28.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.28.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.29.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.29.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.29.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.3.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.3.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.3.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.30.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.30.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.30.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.31.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.31.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.31.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.32.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.32.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.32.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.33.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.33.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.33.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.34.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.34.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.34.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.35.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.35.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.35.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.36.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.36.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.36.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.37.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.37.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.37.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.38.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.38.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.38.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.39.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.39.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.39.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.4.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.4.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.4.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.40.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.40.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.40.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.41.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.41.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.41.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.42.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.42.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.42.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.43.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.43.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.43.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.44.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.44.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.44.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.45.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.45.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.45.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.46.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.46.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.46.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.47.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.47.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.47.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.48.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.48.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.48.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.49.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.49.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.49.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.5.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.5.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.5.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.50.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.50.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.50.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.51.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.51.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.51.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.52.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.52.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.52.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.53.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.53.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.53.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.54.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.54.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.54.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.55.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.55.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.55.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.56.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.56.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.56.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.57.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.57.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.57.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.58.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.58.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.58.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.59.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.59.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.59.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.6.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.6.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.6.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.60.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.60.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.60.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.61.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.61.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.61.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.62.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.62.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.62.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.63.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.63.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.63.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.64.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.64.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.64.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.65.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.65.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.65.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.66.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.66.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.66.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.67.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.67.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.67.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.68.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.68.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.68.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.69.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.69.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.69.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.7.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.7.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.7.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.70.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.70.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.70.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.71.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.71.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.71.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.72.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.72.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.72.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.73.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.73.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.73.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.74.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.74.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.74.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.75.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.75.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.75.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.76.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.76.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.76.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.77.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.77.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.77.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.78.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.78.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.78.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.79.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.79.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.79.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.8.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.8.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.8.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.80.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.80.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.80.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.81.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.81.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.81.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.82.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.82.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.82.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.83.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.83.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.83.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.84.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.84.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.84.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.85.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.85.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.85.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.86.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.86.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.86.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.87.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.87.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.87.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.88.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.88.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.88.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.89.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.89.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.89.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.9.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.9.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.9.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.90.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.90.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.90.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.91.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.91.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.91.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.92.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.92.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.92.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.93.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.93.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.93.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.94.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.94.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.94.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.95.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.95.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.95.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.96.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.96.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.96.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.97.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.97.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.97.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.98.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.98.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.98.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.99.down_proj.weight": "model-00014-of-00049.safetensors", + "model.layers.14.mlp.experts.99.gate_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.experts.99.up_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.mlp.gate.weight": "model-00015-of-00049.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.input_layernorm.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.0.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.0.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.0.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.1.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.1.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.1.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.10.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.10.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.10.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.100.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.100.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.100.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.101.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.101.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.101.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.102.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.102.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.102.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.103.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.103.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.103.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.104.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.104.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.104.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.105.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.105.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.105.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.106.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.106.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.106.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.107.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.107.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.107.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.108.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.108.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.108.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.109.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.109.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.109.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.11.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.11.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.11.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.110.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.110.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.110.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.111.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.111.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.111.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.112.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.112.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.112.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.113.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.113.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.113.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.114.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.114.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.114.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.115.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.115.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.115.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.116.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.116.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.116.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.117.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.117.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.117.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.118.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.118.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.118.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.119.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.119.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.119.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.12.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.12.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.12.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.120.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.120.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.120.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.121.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.121.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.121.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.122.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.122.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.122.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.123.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.123.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.123.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.124.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.124.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.124.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.125.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.125.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.125.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.126.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.126.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.126.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.127.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.127.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.127.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.13.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.13.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.13.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.14.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.14.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.14.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.15.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.15.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.15.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.16.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.16.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.16.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.17.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.17.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.17.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.18.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.18.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.18.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.19.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.19.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.19.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.2.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.2.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.2.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.20.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.20.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.20.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.21.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.21.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.21.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.22.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.22.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.22.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.23.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.23.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.23.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.24.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.24.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.24.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.25.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.25.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.25.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.26.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.26.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.26.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.27.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.27.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.27.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.28.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.28.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.28.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.29.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.29.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.29.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.3.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.3.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.3.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.30.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.30.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.30.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.31.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.31.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.31.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.32.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.32.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.32.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.33.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.33.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.33.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.34.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.34.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.34.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.35.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.35.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.35.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.36.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.36.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.36.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.37.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.37.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.37.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.38.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.38.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.38.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.39.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.39.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.39.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.4.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.4.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.4.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.40.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.40.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.40.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.41.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.41.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.41.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.42.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.42.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.42.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.43.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.43.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.43.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.44.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.44.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.44.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.45.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.45.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.45.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.46.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.46.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.46.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.47.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.47.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.47.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.48.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.48.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.48.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.49.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.49.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.49.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.5.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.5.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.5.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.50.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.50.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.50.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.51.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.51.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.51.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.52.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.52.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.52.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.53.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.53.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.53.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.54.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.54.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.54.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.55.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.55.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.55.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.56.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.56.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.56.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.57.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.57.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.57.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.58.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.58.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.58.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.59.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.59.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.59.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.6.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.6.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.6.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.60.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.60.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.60.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.61.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.61.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.61.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.62.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.62.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.62.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.63.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.63.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.63.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.64.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.64.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.64.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.65.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.65.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.65.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.66.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.66.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.66.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.67.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.67.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.67.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.68.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.68.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.68.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.69.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.69.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.69.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.7.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.7.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.7.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.70.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.70.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.70.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.71.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.71.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.71.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.72.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.72.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.72.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.73.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.73.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.73.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.74.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.74.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.74.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.75.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.75.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.75.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.76.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.76.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.76.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.77.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.77.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.77.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.78.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.78.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.78.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.79.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.79.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.79.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.8.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.8.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.8.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.80.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.80.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.80.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.81.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.81.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.81.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.82.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.82.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.82.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.83.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.83.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.83.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.84.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.84.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.84.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.85.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.85.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.85.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.86.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.86.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.86.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.87.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.87.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.87.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.88.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.88.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.88.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.89.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.89.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.89.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.9.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.9.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.9.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.90.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.90.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.90.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.91.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.91.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.91.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.92.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.92.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.92.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.93.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.93.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.93.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.94.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.94.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.94.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.95.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.95.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.95.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.96.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.96.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.96.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.97.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.97.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.97.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.98.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.98.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.98.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.99.down_proj.weight": "model-00015-of-00049.safetensors", + "model.layers.15.mlp.experts.99.gate_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.experts.99.up_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.mlp.gate.weight": "model-00016-of-00049.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.input_layernorm.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.0.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.0.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.0.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.1.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.1.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.1.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.10.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.10.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.10.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.100.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.100.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.100.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.101.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.101.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.101.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.102.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.102.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.102.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.103.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.103.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.103.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.104.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.104.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.104.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.105.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.105.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.105.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.106.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.106.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.106.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.107.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.107.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.107.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.108.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.108.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.108.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.109.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.109.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.109.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.11.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.11.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.11.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.110.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.110.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.110.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.111.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.111.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.111.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.112.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.112.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.112.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.113.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.113.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.113.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.114.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.114.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.114.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.115.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.115.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.115.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.116.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.116.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.116.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.117.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.117.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.117.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.118.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.118.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.118.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.119.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.119.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.119.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.12.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.12.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.12.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.120.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.120.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.120.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.121.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.121.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.121.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.122.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.122.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.122.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.123.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.123.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.123.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.124.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.124.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.124.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.125.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.125.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.125.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.126.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.126.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.126.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.127.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.127.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.127.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.13.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.13.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.13.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.14.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.14.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.14.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.15.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.15.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.15.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.16.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.16.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.16.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.17.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.17.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.17.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.18.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.18.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.18.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.19.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.19.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.19.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.2.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.2.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.2.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.20.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.20.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.20.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.21.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.21.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.21.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.22.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.22.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.22.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.23.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.23.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.23.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.24.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.24.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.24.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.25.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.25.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.25.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.26.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.26.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.26.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.27.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.27.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.27.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.28.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.28.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.28.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.29.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.29.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.29.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.3.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.3.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.3.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.30.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.30.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.30.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.31.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.31.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.31.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.32.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.32.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.32.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.33.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.33.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.33.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.34.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.34.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.34.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.35.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.35.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.35.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.36.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.36.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.36.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.37.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.37.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.37.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.38.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.38.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.38.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.39.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.39.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.39.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.4.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.4.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.4.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.40.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.40.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.40.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.41.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.41.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.41.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.42.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.42.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.42.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.43.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.43.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.43.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.44.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.44.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.44.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.45.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.45.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.45.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.46.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.46.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.46.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.47.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.47.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.47.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.48.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.48.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.48.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.49.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.49.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.49.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.5.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.5.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.5.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.50.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.50.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.50.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.51.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.51.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.51.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.52.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.52.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.52.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.53.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.53.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.53.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.54.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.54.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.54.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.55.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.55.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.55.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.56.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.56.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.56.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.57.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.57.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.57.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.58.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.58.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.58.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.59.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.59.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.59.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.6.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.6.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.6.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.60.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.60.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.60.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.61.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.61.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.61.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.62.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.62.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.62.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.63.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.63.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.63.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.64.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.64.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.64.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.65.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.65.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.65.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.66.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.66.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.66.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.67.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.67.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.67.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.68.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.68.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.68.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.69.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.69.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.69.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.7.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.7.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.7.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.70.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.70.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.70.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.71.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.71.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.71.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.72.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.72.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.72.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.73.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.73.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.73.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.74.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.74.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.74.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.75.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.75.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.75.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.76.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.76.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.76.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.77.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.77.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.77.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.78.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.78.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.78.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.79.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.79.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.79.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.8.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.8.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.8.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.80.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.80.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.80.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.81.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.81.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.81.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.82.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.82.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.82.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.83.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.83.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.83.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.84.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.84.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.84.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.85.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.85.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.85.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.86.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.86.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.86.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.87.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.87.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.87.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.88.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.88.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.88.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.89.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.89.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.89.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.9.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.9.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.9.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.90.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.90.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.90.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.91.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.91.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.91.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.92.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.92.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.92.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.93.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.93.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.93.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.94.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.94.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.94.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.95.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.95.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.95.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.96.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.96.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.96.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.97.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.97.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.97.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.98.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.98.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.98.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.99.down_proj.weight": "model-00016-of-00049.safetensors", + "model.layers.16.mlp.experts.99.gate_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.experts.99.up_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.mlp.gate.weight": "model-00017-of-00049.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.input_layernorm.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.0.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.0.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.0.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.1.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.1.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.1.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.10.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.10.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.10.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.100.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.100.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.100.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.101.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.101.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.101.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.102.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.102.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.102.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.103.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.103.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.103.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.104.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.104.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.104.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.105.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.105.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.105.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.106.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.106.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.106.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.107.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.107.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.107.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.108.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.108.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.108.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.109.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.109.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.109.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.11.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.11.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.11.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.110.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.110.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.110.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.111.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.111.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.111.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.112.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.112.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.112.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.113.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.113.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.113.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.114.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.114.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.114.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.115.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.115.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.115.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.116.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.116.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.116.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.117.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.117.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.117.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.118.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.118.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.118.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.119.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.119.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.119.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.12.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.12.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.12.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.120.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.120.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.120.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.121.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.121.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.121.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.122.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.122.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.122.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.123.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.123.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.123.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.124.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.124.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.124.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.125.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.125.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.125.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.126.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.126.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.126.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.127.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.127.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.127.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.13.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.13.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.13.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.14.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.14.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.14.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.15.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.15.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.15.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.16.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.16.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.16.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.17.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.17.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.17.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.18.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.18.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.18.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.19.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.19.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.19.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.2.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.2.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.2.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.20.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.20.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.20.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.21.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.21.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.21.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.22.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.22.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.22.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.23.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.23.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.23.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.24.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.24.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.24.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.25.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.25.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.25.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.26.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.26.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.26.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.27.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.27.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.27.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.28.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.28.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.28.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.29.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.29.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.29.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.3.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.3.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.3.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.30.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.30.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.30.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.31.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.31.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.31.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.32.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.32.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.32.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.33.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.33.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.33.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.34.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.34.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.34.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.35.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.35.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.35.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.36.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.36.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.36.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.37.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.37.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.37.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.38.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.38.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.38.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.39.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.39.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.39.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.4.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.4.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.4.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.40.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.40.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.40.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.41.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.41.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.41.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.42.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.42.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.42.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.43.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.43.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.43.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.44.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.44.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.44.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.45.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.45.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.45.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.46.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.46.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.46.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.47.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.47.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.47.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.48.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.48.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.48.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.49.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.49.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.49.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.5.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.5.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.5.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.50.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.50.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.50.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.51.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.51.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.51.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.52.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.52.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.52.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.53.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.53.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.53.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.54.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.54.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.54.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.55.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.55.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.55.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.56.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.56.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.56.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.57.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.57.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.57.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.58.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.58.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.58.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.59.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.59.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.59.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.6.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.6.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.6.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.60.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.60.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.60.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.61.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.61.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.61.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.62.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.62.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.62.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.63.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.63.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.63.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.64.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.64.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.64.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.65.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.65.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.65.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.66.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.66.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.66.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.67.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.67.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.67.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.68.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.68.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.68.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.69.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.69.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.69.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.7.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.7.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.7.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.70.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.70.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.70.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.71.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.71.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.71.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.72.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.72.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.72.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.73.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.73.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.73.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.74.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.74.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.74.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.75.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.75.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.75.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.76.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.76.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.76.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.77.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.77.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.77.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.78.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.78.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.78.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.79.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.79.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.79.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.8.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.8.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.8.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.80.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.80.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.80.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.81.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.81.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.81.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.82.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.82.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.82.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.83.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.83.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.83.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.84.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.84.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.84.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.85.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.85.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.85.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.86.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.86.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.86.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.87.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.87.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.87.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.88.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.88.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.88.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.89.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.89.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.89.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.9.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.9.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.9.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.90.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.90.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.90.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.91.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.91.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.91.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.92.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.92.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.92.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.93.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.93.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.93.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.94.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.94.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.94.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.95.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.95.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.95.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.96.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.96.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.96.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.97.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.97.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.97.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.98.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.98.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.98.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.99.down_proj.weight": "model-00017-of-00049.safetensors", + "model.layers.17.mlp.experts.99.gate_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.experts.99.up_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.mlp.gate.weight": "model-00018-of-00049.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.input_layernorm.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.0.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.0.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.0.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.1.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.1.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.1.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.10.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.10.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.10.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.100.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.100.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.100.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.101.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.101.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.101.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.102.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.102.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.102.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.103.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.103.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.103.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.104.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.104.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.104.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.105.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.105.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.105.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.106.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.106.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.106.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.107.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.107.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.107.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.108.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.108.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.108.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.109.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.109.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.109.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.11.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.11.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.11.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.110.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.110.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.110.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.111.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.111.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.111.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.112.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.112.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.112.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.113.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.113.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.113.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.114.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.114.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.114.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.115.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.115.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.115.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.116.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.116.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.116.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.117.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.117.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.117.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.118.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.118.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.118.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.119.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.119.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.119.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.12.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.12.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.12.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.120.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.120.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.120.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.121.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.121.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.121.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.122.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.122.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.122.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.123.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.123.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.123.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.124.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.124.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.124.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.125.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.125.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.125.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.126.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.126.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.126.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.127.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.127.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.127.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.13.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.13.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.13.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.14.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.14.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.14.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.15.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.15.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.15.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.16.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.16.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.16.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.17.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.17.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.17.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.18.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.18.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.18.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.19.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.19.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.19.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.2.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.2.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.2.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.20.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.20.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.20.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.21.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.21.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.21.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.22.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.22.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.22.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.23.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.23.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.23.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.24.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.24.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.24.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.25.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.25.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.25.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.26.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.26.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.26.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.27.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.27.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.27.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.28.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.28.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.28.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.29.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.29.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.29.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.3.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.3.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.3.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.30.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.30.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.30.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.31.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.31.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.31.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.32.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.32.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.32.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.33.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.33.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.33.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.34.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.34.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.34.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.35.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.35.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.35.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.36.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.36.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.36.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.37.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.37.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.37.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.38.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.38.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.38.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.39.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.39.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.39.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.4.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.4.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.4.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.40.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.40.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.40.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.41.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.41.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.41.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.42.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.42.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.42.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.43.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.43.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.43.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.44.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.44.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.44.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.45.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.45.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.45.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.46.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.46.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.46.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.47.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.47.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.47.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.48.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.48.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.48.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.49.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.49.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.49.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.5.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.5.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.5.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.50.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.50.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.50.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.51.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.51.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.51.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.52.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.52.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.52.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.53.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.53.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.53.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.54.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.54.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.54.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.55.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.55.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.55.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.56.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.56.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.56.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.57.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.57.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.57.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.58.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.58.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.58.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.59.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.59.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.59.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.6.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.6.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.6.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.60.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.60.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.60.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.61.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.61.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.61.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.62.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.62.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.62.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.63.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.63.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.63.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.64.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.64.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.64.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.65.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.65.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.65.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.66.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.66.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.66.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.67.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.67.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.67.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.68.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.68.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.68.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.69.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.69.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.69.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.7.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.7.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.7.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.70.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.70.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.70.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.71.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.71.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.71.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.72.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.72.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.72.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.73.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.73.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.73.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.74.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.74.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.74.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.75.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.75.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.75.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.76.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.76.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.76.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.77.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.77.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.77.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.78.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.78.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.78.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.79.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.79.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.79.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.8.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.8.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.8.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.80.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.80.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.80.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.81.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.81.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.81.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.82.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.82.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.82.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.83.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.83.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.83.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.84.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.84.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.84.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.85.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.85.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.85.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.86.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.86.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.86.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.87.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.87.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.87.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.88.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.88.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.88.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.89.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.89.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.89.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.9.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.9.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.9.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.90.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.90.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.90.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.91.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.91.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.91.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.92.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.92.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.92.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.93.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.93.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.93.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.94.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.94.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.94.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.95.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.95.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.95.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.96.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.96.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.96.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.97.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.97.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.97.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.98.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.98.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.98.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.99.down_proj.weight": "model-00018-of-00049.safetensors", + "model.layers.18.mlp.experts.99.gate_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.experts.99.up_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.mlp.gate.weight": "model-00019-of-00049.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.input_layernorm.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.0.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.0.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.0.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.1.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.1.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.1.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.10.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.10.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.10.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.100.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.100.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.100.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.101.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.101.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.101.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.102.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.102.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.102.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.103.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.103.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.103.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.104.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.104.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.104.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.105.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.105.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.105.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.106.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.106.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.106.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.107.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.107.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.107.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.108.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.108.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.108.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.109.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.109.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.109.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.11.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.11.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.11.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.110.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.110.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.110.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.111.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.111.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.111.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.112.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.112.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.112.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.113.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.113.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.113.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.114.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.114.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.114.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.115.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.115.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.115.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.116.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.116.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.116.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.117.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.117.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.117.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.118.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.118.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.118.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.119.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.119.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.119.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.12.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.12.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.12.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.120.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.120.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.120.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.121.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.121.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.121.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.122.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.122.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.122.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.123.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.123.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.123.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.124.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.124.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.124.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.125.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.125.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.125.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.126.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.126.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.126.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.127.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.127.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.127.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.13.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.13.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.13.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.14.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.14.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.14.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.15.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.15.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.15.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.16.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.16.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.16.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.17.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.17.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.17.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.18.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.18.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.18.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.19.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.19.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.19.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.2.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.2.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.2.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.20.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.20.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.20.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.21.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.21.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.21.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.22.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.22.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.22.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.23.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.23.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.23.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.24.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.24.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.24.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.25.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.25.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.25.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.26.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.26.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.26.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.27.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.27.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.27.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.28.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.28.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.28.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.29.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.29.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.29.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.3.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.3.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.3.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.30.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.30.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.30.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.31.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.31.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.31.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.32.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.32.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.32.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.33.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.33.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.33.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.34.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.34.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.34.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.35.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.35.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.35.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.36.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.36.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.36.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.37.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.37.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.37.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.38.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.38.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.38.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.39.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.39.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.39.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.4.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.4.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.4.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.40.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.40.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.40.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.41.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.41.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.41.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.42.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.42.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.42.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.43.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.43.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.43.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.44.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.44.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.44.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.45.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.45.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.45.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.46.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.46.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.46.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.47.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.47.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.47.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.48.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.48.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.48.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.49.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.49.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.49.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.5.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.5.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.5.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.50.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.50.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.50.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.51.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.51.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.51.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.52.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.52.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.52.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.53.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.53.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.53.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.54.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.54.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.54.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.55.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.55.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.55.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.56.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.56.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.56.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.57.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.57.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.57.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.58.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.58.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.58.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.59.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.59.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.59.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.6.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.6.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.6.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.60.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.60.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.60.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.61.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.61.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.61.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.62.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.62.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.62.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.63.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.63.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.63.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.64.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.64.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.64.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.65.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.65.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.65.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.66.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.66.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.66.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.67.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.67.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.67.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.68.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.68.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.68.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.69.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.69.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.69.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.7.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.7.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.7.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.70.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.70.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.70.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.71.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.71.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.71.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.72.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.72.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.72.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.73.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.73.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.73.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.74.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.74.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.74.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.75.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.75.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.75.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.76.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.76.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.76.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.77.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.77.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.77.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.78.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.78.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.78.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.79.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.79.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.79.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.8.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.8.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.8.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.80.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.80.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.80.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.81.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.81.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.81.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.82.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.82.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.82.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.83.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.83.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.83.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.84.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.84.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.84.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.85.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.85.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.85.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.86.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.86.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.86.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.87.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.87.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.87.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.88.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.88.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.88.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.89.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.89.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.89.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.9.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.9.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.9.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.90.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.90.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.90.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.91.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.91.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.91.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.92.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.92.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.92.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.93.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.93.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.93.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.94.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.94.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.94.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.95.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.95.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.95.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.96.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.96.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.96.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.97.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.97.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.97.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.98.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.98.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.98.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.99.down_proj.weight": "model-00019-of-00049.safetensors", + "model.layers.19.mlp.experts.99.gate_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.experts.99.up_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.mlp.gate.weight": "model-00020-of-00049.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.2.input_layernorm.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.0.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.0.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.0.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.1.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.1.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.1.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.10.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.10.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.10.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.100.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.100.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.100.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.101.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.101.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.101.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.102.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.102.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.102.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.103.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.103.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.103.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.104.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.104.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.104.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.105.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.105.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.105.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.106.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.106.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.106.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.107.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.107.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.107.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.108.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.108.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.108.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.109.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.109.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.109.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.11.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.11.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.11.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.110.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.110.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.110.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.111.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.111.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.111.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.112.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.112.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.112.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.113.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.113.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.113.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.114.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.114.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.114.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.115.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.115.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.115.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.116.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.116.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.116.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.117.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.117.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.117.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.118.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.118.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.118.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.119.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.119.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.119.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.12.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.12.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.12.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.120.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.120.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.120.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.121.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.121.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.121.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.122.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.122.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.122.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.123.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.123.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.123.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.124.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.124.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.124.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.125.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.125.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.125.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.126.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.126.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.126.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.127.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.127.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.127.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.13.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.13.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.13.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.14.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.14.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.14.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.15.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.15.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.15.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.16.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.16.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.16.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.17.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.17.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.17.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.18.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.18.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.18.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.19.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.19.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.19.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.2.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.2.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.2.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.20.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.20.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.20.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.21.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.21.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.21.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.22.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.22.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.22.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.23.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.23.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.23.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.24.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.24.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.24.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.25.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.25.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.25.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.26.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.26.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.26.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.27.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.27.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.27.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.28.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.28.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.28.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.29.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.29.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.29.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.3.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.3.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.3.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.30.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.30.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.30.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.31.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.31.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.31.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.32.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.32.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.32.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.33.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.33.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.33.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.34.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.34.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.34.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.35.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.35.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.35.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.36.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.36.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.36.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.37.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.37.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.37.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.38.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.38.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.38.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.39.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.39.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.39.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.4.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.4.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.4.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.40.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.40.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.40.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.41.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.41.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.41.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.42.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.42.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.42.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.43.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.43.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.43.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.44.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.44.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.44.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.45.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.45.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.45.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.46.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.46.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.46.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.47.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.47.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.47.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.48.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.48.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.48.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.49.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.49.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.49.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.5.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.5.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.5.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.50.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.50.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.50.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.51.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.51.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.51.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.52.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.52.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.52.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.53.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.53.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.53.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.54.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.54.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.54.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.55.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.55.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.55.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.56.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.56.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.56.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.57.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.57.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.57.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.58.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.58.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.58.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.59.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.59.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.59.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.6.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.6.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.6.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.60.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.60.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.60.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.61.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.61.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.61.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.62.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.62.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.62.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.63.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.63.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.63.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.64.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.64.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.64.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.65.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.65.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.65.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.66.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.66.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.66.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.67.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.67.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.67.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.68.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.68.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.68.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.69.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.69.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.69.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.7.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.7.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.7.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.70.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.70.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.70.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.71.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.71.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.71.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.72.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.72.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.72.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.73.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.73.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.73.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.74.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.74.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.74.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.75.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.75.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.75.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.76.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.76.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.76.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.77.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.77.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.77.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.78.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.78.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.78.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.79.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.79.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.79.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.8.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.8.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.8.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.80.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.80.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.80.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.81.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.81.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.81.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.82.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.82.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.82.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.83.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.83.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.83.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.84.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.84.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.84.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.85.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.85.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.85.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.86.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.86.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.86.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.87.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.87.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.87.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.88.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.88.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.88.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.89.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.89.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.89.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.9.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.9.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.9.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.90.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.90.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.90.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.91.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.91.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.91.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.92.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.92.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.92.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.93.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.93.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.93.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.94.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.94.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.94.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.95.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.95.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.95.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.96.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.96.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.96.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.97.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.97.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.97.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.98.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.98.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.98.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.99.down_proj.weight": "model-00002-of-00049.safetensors", + "model.layers.2.mlp.experts.99.gate_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.experts.99.up_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.mlp.gate.weight": "model-00003-of-00049.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.20.input_layernorm.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.0.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.0.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.0.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.1.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.1.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.1.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.10.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.10.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.10.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.100.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.100.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.100.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.101.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.101.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.101.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.102.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.102.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.102.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.103.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.103.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.103.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.104.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.104.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.104.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.105.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.105.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.105.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.106.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.106.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.106.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.107.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.107.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.107.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.108.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.108.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.108.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.109.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.109.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.109.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.11.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.11.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.11.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.110.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.110.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.110.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.111.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.111.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.111.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.112.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.112.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.112.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.113.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.113.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.113.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.114.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.114.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.114.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.115.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.115.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.115.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.116.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.116.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.116.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.117.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.117.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.117.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.118.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.118.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.118.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.119.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.119.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.119.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.12.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.12.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.12.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.120.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.120.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.120.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.121.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.121.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.121.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.122.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.122.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.122.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.123.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.123.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.123.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.124.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.124.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.124.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.125.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.125.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.125.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.126.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.126.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.126.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.127.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.127.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.127.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.13.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.13.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.13.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.14.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.14.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.14.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.15.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.15.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.15.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.16.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.16.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.16.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.17.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.17.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.17.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.18.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.18.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.18.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.19.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.19.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.19.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.2.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.2.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.2.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.20.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.20.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.20.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.21.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.21.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.21.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.22.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.22.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.22.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.23.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.23.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.23.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.24.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.24.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.24.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.25.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.25.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.25.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.26.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.26.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.26.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.27.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.27.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.27.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.28.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.28.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.28.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.29.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.29.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.29.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.3.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.3.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.3.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.30.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.30.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.30.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.31.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.31.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.31.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.32.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.32.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.32.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.33.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.33.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.33.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.34.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.34.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.34.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.35.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.35.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.35.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.36.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.36.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.36.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.37.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.37.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.37.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.38.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.38.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.38.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.39.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.39.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.39.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.4.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.4.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.4.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.40.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.40.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.40.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.41.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.41.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.41.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.42.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.42.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.42.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.43.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.43.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.43.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.44.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.44.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.44.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.45.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.45.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.45.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.46.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.46.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.46.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.47.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.47.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.47.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.48.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.48.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.48.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.49.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.49.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.49.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.5.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.5.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.5.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.50.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.50.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.50.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.51.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.51.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.51.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.52.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.52.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.52.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.53.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.53.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.53.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.54.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.54.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.54.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.55.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.55.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.55.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.56.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.56.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.56.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.57.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.57.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.57.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.58.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.58.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.58.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.59.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.59.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.59.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.6.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.6.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.6.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.60.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.60.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.60.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.61.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.61.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.61.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.62.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.62.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.62.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.63.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.63.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.63.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.64.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.64.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.64.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.65.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.65.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.65.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.66.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.66.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.66.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.67.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.67.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.67.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.68.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.68.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.68.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.69.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.69.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.69.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.7.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.7.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.7.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.70.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.70.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.70.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.71.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.71.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.71.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.72.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.72.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.72.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.73.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.73.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.73.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.74.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.74.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.74.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.75.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.75.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.75.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.76.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.76.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.76.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.77.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.77.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.77.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.78.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.78.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.78.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.79.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.79.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.79.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.8.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.8.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.8.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.80.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.80.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.80.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.81.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.81.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.81.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.82.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.82.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.82.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.83.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.83.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.83.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.84.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.84.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.84.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.85.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.85.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.85.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.86.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.86.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.86.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.87.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.87.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.87.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.88.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.88.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.88.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.89.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.89.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.89.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.9.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.9.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.9.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.90.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.90.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.90.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.91.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.91.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.91.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.92.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.92.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.92.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.93.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.93.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.93.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.94.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.94.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.94.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.95.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.95.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.95.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.96.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.96.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.96.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.97.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.97.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.97.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.98.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.98.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.98.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.99.down_proj.weight": "model-00020-of-00049.safetensors", + "model.layers.20.mlp.experts.99.gate_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.experts.99.up_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.mlp.gate.weight": "model-00021-of-00049.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.input_layernorm.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.0.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.0.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.0.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.1.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.1.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.1.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.10.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.10.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.10.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.100.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.100.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.100.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.101.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.101.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.101.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.102.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.102.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.102.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.103.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.103.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.103.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.104.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.104.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.104.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.105.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.105.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.105.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.106.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.106.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.106.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.107.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.107.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.107.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.108.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.108.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.108.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.109.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.109.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.109.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.11.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.11.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.11.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.110.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.110.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.110.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.111.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.111.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.111.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.112.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.112.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.112.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.113.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.113.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.113.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.114.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.114.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.114.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.115.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.115.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.115.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.116.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.116.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.116.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.117.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.117.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.117.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.118.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.118.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.118.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.119.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.119.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.119.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.12.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.12.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.12.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.120.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.120.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.120.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.121.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.121.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.121.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.122.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.122.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.122.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.123.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.123.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.123.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.124.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.124.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.124.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.125.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.125.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.125.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.126.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.126.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.126.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.127.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.127.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.127.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.13.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.13.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.13.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.14.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.14.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.14.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.15.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.15.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.15.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.16.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.16.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.16.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.17.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.17.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.17.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.18.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.18.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.18.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.19.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.19.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.19.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.2.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.2.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.2.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.20.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.20.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.20.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.21.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.21.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.21.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.22.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.22.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.22.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.23.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.23.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.23.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.24.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.24.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.24.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.25.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.25.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.25.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.26.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.26.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.26.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.27.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.27.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.27.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.28.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.28.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.28.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.29.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.29.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.29.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.3.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.3.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.3.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.30.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.30.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.30.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.31.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.31.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.31.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.32.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.32.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.32.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.33.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.33.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.33.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.34.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.34.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.34.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.35.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.35.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.35.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.36.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.36.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.36.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.37.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.37.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.37.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.38.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.38.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.38.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.39.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.39.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.39.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.4.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.4.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.4.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.40.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.40.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.40.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.41.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.41.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.41.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.42.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.42.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.42.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.43.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.43.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.43.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.44.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.44.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.44.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.45.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.45.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.45.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.46.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.46.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.46.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.47.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.47.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.47.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.48.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.48.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.48.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.49.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.49.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.49.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.5.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.5.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.5.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.50.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.50.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.50.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.51.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.51.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.51.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.52.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.52.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.52.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.53.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.53.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.53.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.54.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.54.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.54.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.55.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.55.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.55.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.56.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.56.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.56.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.57.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.57.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.57.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.58.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.58.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.58.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.59.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.59.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.59.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.6.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.6.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.6.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.60.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.60.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.60.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.61.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.61.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.61.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.62.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.62.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.62.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.63.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.63.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.63.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.64.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.64.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.64.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.65.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.65.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.65.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.66.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.66.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.66.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.67.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.67.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.67.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.68.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.68.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.68.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.69.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.69.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.69.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.7.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.7.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.7.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.70.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.70.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.70.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.71.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.71.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.71.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.72.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.72.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.72.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.73.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.73.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.73.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.74.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.74.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.74.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.75.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.75.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.75.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.76.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.76.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.76.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.77.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.77.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.77.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.78.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.78.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.78.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.79.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.79.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.79.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.8.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.8.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.8.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.80.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.80.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.80.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.81.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.81.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.81.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.82.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.82.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.82.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.83.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.83.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.83.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.84.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.84.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.84.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.85.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.85.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.85.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.86.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.86.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.86.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.87.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.87.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.87.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.88.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.88.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.88.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.89.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.89.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.89.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.9.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.9.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.9.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.90.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.90.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.90.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.91.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.91.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.91.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.92.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.92.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.92.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.93.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.93.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.93.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.94.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.94.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.94.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.95.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.95.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.95.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.96.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.96.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.96.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.97.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.97.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.97.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.98.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.98.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.98.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.99.down_proj.weight": "model-00021-of-00049.safetensors", + "model.layers.21.mlp.experts.99.gate_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.experts.99.up_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.mlp.gate.weight": "model-00022-of-00049.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.input_layernorm.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.0.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.0.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.0.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.1.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.1.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.1.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.10.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.10.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.10.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.100.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.100.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.100.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.101.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.101.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.101.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.102.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.102.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.102.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.103.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.103.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.103.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.104.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.104.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.104.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.105.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.105.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.105.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.106.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.106.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.106.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.107.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.107.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.107.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.108.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.108.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.108.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.109.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.109.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.109.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.11.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.11.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.11.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.110.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.110.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.110.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.111.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.111.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.111.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.112.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.112.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.112.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.113.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.113.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.113.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.114.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.114.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.114.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.115.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.115.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.115.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.116.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.116.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.116.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.117.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.117.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.117.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.118.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.118.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.118.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.119.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.119.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.119.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.12.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.12.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.12.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.120.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.120.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.120.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.121.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.121.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.121.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.122.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.122.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.122.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.123.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.123.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.123.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.124.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.124.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.124.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.125.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.125.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.125.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.126.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.126.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.126.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.127.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.127.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.127.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.13.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.13.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.13.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.14.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.14.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.14.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.15.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.15.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.15.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.16.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.16.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.16.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.17.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.17.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.17.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.18.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.18.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.18.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.19.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.19.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.19.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.2.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.2.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.2.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.20.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.20.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.20.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.21.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.21.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.21.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.22.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.22.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.22.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.23.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.23.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.23.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.24.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.24.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.24.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.25.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.25.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.25.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.26.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.26.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.26.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.27.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.27.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.27.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.28.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.28.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.28.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.29.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.29.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.29.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.3.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.3.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.3.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.30.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.30.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.30.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.31.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.31.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.31.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.32.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.32.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.32.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.33.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.33.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.33.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.34.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.34.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.34.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.35.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.35.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.35.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.36.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.36.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.36.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.37.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.37.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.37.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.38.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.38.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.38.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.39.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.39.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.39.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.4.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.4.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.4.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.40.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.40.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.40.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.41.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.41.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.41.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.42.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.42.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.42.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.43.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.43.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.43.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.44.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.44.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.44.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.45.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.45.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.45.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.46.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.46.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.46.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.47.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.47.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.47.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.48.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.48.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.48.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.49.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.49.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.49.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.5.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.5.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.5.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.50.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.50.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.50.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.51.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.51.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.51.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.52.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.52.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.52.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.53.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.53.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.53.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.54.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.54.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.54.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.55.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.55.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.55.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.56.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.56.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.56.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.57.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.57.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.57.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.58.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.58.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.58.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.59.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.59.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.59.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.6.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.6.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.6.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.60.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.60.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.60.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.61.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.61.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.61.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.62.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.62.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.62.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.63.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.63.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.63.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.64.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.64.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.64.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.65.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.65.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.65.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.66.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.66.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.66.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.67.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.67.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.67.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.68.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.68.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.68.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.69.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.69.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.69.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.7.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.7.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.7.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.70.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.70.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.70.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.71.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.71.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.71.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.72.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.72.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.72.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.73.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.73.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.73.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.74.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.74.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.74.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.75.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.75.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.75.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.76.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.76.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.76.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.77.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.77.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.77.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.78.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.78.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.78.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.79.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.79.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.79.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.8.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.8.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.8.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.80.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.80.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.80.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.81.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.81.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.81.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.82.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.82.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.82.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.83.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.83.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.83.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.84.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.84.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.84.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.85.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.85.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.85.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.86.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.86.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.86.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.87.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.87.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.87.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.88.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.88.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.88.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.89.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.89.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.89.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.9.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.9.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.9.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.90.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.90.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.90.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.91.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.91.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.91.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.92.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.92.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.92.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.93.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.93.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.93.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.94.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.94.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.94.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.95.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.95.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.95.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.96.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.96.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.96.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.97.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.97.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.97.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.98.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.98.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.98.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.99.down_proj.weight": "model-00022-of-00049.safetensors", + "model.layers.22.mlp.experts.99.gate_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.experts.99.up_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.mlp.gate.weight": "model-00023-of-00049.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.input_layernorm.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.0.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.0.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.0.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.1.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.1.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.1.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.10.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.10.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.10.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.100.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.100.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.100.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.101.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.101.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.101.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.102.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.102.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.102.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.103.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.103.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.103.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.104.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.104.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.104.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.105.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.105.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.105.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.106.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.106.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.106.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.107.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.107.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.107.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.108.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.108.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.108.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.109.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.109.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.109.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.11.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.11.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.11.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.110.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.110.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.110.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.111.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.111.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.111.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.112.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.112.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.112.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.113.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.113.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.113.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.114.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.114.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.114.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.115.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.115.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.115.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.116.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.116.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.116.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.117.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.117.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.117.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.118.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.118.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.118.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.119.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.119.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.119.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.12.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.12.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.12.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.120.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.120.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.120.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.121.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.121.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.121.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.122.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.122.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.122.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.123.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.123.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.123.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.124.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.124.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.124.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.125.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.125.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.125.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.126.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.126.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.126.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.127.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.127.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.127.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.13.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.13.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.13.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.14.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.14.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.14.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.15.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.15.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.15.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.16.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.16.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.16.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.17.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.17.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.17.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.18.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.18.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.18.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.19.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.19.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.19.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.2.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.2.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.2.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.20.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.20.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.20.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.21.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.21.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.21.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.22.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.22.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.22.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.23.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.23.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.23.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.24.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.24.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.24.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.25.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.25.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.25.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.26.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.26.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.26.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.27.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.27.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.27.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.28.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.28.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.28.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.29.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.29.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.29.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.3.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.3.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.3.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.30.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.30.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.30.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.31.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.31.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.31.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.32.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.32.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.32.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.33.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.33.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.33.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.34.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.34.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.34.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.35.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.35.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.35.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.36.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.36.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.36.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.37.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.37.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.37.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.38.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.38.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.38.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.39.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.39.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.39.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.4.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.4.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.4.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.40.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.40.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.40.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.41.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.41.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.41.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.42.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.42.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.42.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.43.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.43.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.43.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.44.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.44.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.44.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.45.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.45.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.45.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.46.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.46.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.46.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.47.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.47.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.47.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.48.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.48.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.48.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.49.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.49.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.49.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.5.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.5.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.5.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.50.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.50.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.50.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.51.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.51.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.51.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.52.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.52.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.52.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.53.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.53.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.53.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.54.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.54.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.54.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.55.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.55.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.55.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.56.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.56.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.56.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.57.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.57.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.57.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.58.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.58.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.58.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.59.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.59.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.59.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.6.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.6.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.6.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.60.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.60.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.60.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.61.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.61.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.61.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.62.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.62.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.62.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.63.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.63.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.63.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.64.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.64.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.64.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.65.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.65.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.65.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.66.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.66.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.66.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.67.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.67.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.67.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.68.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.68.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.68.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.69.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.69.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.69.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.7.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.7.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.7.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.70.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.70.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.70.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.71.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.71.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.71.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.72.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.72.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.72.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.73.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.73.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.73.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.74.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.74.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.74.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.75.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.75.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.75.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.76.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.76.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.76.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.77.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.77.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.77.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.78.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.78.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.78.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.79.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.79.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.79.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.8.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.8.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.8.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.80.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.80.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.80.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.81.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.81.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.81.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.82.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.82.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.82.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.83.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.83.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.83.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.84.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.84.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.84.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.85.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.85.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.85.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.86.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.86.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.86.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.87.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.87.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.87.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.88.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.88.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.88.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.89.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.89.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.89.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.9.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.9.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.9.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.90.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.90.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.90.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.91.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.91.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.91.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.92.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.92.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.92.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.93.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.93.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.93.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.94.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.94.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.94.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.95.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.95.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.95.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.96.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.96.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.96.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.97.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.97.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.97.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.98.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.98.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.98.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.99.down_proj.weight": "model-00023-of-00049.safetensors", + "model.layers.23.mlp.experts.99.gate_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.experts.99.up_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.mlp.gate.weight": "model-00024-of-00049.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.input_layernorm.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.0.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.0.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.0.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.1.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.1.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.1.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.10.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.10.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.10.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.100.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.100.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.100.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.101.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.101.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.101.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.102.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.102.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.102.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.103.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.103.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.103.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.104.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.104.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.104.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.105.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.105.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.105.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.106.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.106.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.106.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.107.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.107.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.107.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.108.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.108.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.108.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.109.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.109.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.109.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.11.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.11.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.11.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.110.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.110.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.110.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.111.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.111.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.111.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.112.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.112.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.112.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.113.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.113.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.113.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.114.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.114.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.114.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.115.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.115.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.115.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.116.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.116.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.116.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.117.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.117.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.117.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.118.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.118.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.118.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.119.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.119.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.119.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.12.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.12.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.12.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.120.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.120.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.120.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.121.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.121.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.121.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.122.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.122.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.122.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.123.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.123.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.123.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.124.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.124.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.124.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.125.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.125.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.125.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.126.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.126.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.126.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.127.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.127.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.127.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.13.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.13.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.13.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.14.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.14.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.14.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.15.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.15.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.15.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.16.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.16.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.16.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.17.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.17.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.17.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.18.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.18.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.18.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.19.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.19.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.19.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.2.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.2.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.2.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.20.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.20.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.20.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.21.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.21.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.21.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.22.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.22.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.22.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.23.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.23.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.23.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.24.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.24.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.24.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.25.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.25.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.25.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.26.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.26.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.26.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.27.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.27.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.27.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.28.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.28.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.28.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.29.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.29.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.29.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.3.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.3.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.3.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.30.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.30.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.30.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.31.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.31.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.31.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.32.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.32.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.32.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.33.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.33.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.33.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.34.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.34.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.34.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.35.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.35.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.35.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.36.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.36.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.36.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.37.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.37.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.37.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.38.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.38.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.38.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.39.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.39.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.39.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.4.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.4.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.4.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.40.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.40.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.40.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.41.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.41.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.41.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.42.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.42.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.42.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.43.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.43.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.43.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.44.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.44.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.44.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.45.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.45.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.45.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.46.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.46.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.46.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.47.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.47.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.47.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.48.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.48.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.48.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.49.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.49.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.49.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.5.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.5.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.5.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.50.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.50.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.50.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.51.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.51.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.51.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.52.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.52.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.52.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.53.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.53.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.53.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.54.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.54.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.54.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.55.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.55.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.55.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.56.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.56.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.56.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.57.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.57.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.57.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.58.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.58.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.58.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.59.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.59.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.59.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.6.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.6.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.6.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.60.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.60.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.60.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.61.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.61.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.61.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.62.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.62.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.62.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.63.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.63.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.63.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.64.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.64.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.64.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.65.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.65.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.65.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.66.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.66.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.66.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.67.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.67.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.67.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.68.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.68.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.68.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.69.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.69.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.69.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.7.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.7.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.7.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.70.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.70.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.70.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.71.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.71.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.71.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.72.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.72.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.72.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.73.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.73.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.73.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.74.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.74.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.74.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.75.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.75.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.75.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.76.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.76.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.76.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.77.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.77.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.77.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.78.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.78.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.78.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.79.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.79.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.79.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.8.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.8.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.8.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.80.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.80.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.80.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.81.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.81.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.81.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.82.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.82.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.82.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.83.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.83.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.83.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.84.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.84.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.84.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.85.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.85.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.85.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.86.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.86.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.86.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.87.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.87.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.87.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.88.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.88.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.88.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.89.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.89.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.89.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.9.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.9.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.9.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.90.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.90.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.90.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.91.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.91.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.91.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.92.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.92.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.92.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.93.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.93.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.93.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.94.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.94.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.94.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.95.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.95.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.95.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.96.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.96.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.96.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.97.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.97.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.97.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.98.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.98.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.98.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.99.down_proj.weight": "model-00024-of-00049.safetensors", + "model.layers.24.mlp.experts.99.gate_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.experts.99.up_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.mlp.gate.weight": "model-00025-of-00049.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.input_layernorm.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.0.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.0.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.0.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.1.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.1.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.1.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.10.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.10.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.10.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.100.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.100.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.100.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.101.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.101.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.101.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.102.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.102.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.102.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.103.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.103.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.103.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.104.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.104.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.104.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.105.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.105.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.105.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.106.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.106.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.106.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.107.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.107.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.107.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.108.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.108.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.108.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.109.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.109.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.109.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.11.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.11.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.11.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.110.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.110.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.110.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.111.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.111.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.111.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.112.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.112.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.112.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.113.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.113.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.113.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.114.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.114.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.114.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.115.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.115.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.115.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.116.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.116.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.116.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.117.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.117.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.117.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.118.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.118.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.118.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.119.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.119.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.119.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.12.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.12.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.12.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.120.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.120.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.120.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.121.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.121.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.121.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.122.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.122.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.122.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.123.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.123.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.123.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.124.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.124.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.124.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.125.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.125.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.125.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.126.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.126.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.126.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.127.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.127.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.127.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.13.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.13.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.13.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.14.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.14.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.14.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.15.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.15.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.15.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.16.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.16.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.16.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.17.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.17.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.17.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.18.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.18.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.18.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.19.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.19.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.19.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.2.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.2.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.2.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.20.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.20.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.20.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.21.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.21.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.21.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.22.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.22.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.22.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.23.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.23.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.23.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.24.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.24.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.24.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.25.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.25.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.25.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.26.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.26.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.26.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.27.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.27.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.27.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.28.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.28.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.28.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.29.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.29.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.29.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.3.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.3.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.3.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.30.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.30.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.30.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.31.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.31.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.31.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.32.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.32.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.32.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.33.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.33.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.33.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.34.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.34.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.34.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.35.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.35.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.35.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.36.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.36.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.36.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.37.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.37.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.37.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.38.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.38.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.38.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.39.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.39.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.39.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.4.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.4.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.4.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.40.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.40.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.40.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.41.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.41.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.41.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.42.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.42.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.42.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.43.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.43.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.43.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.44.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.44.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.44.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.45.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.45.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.45.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.46.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.46.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.46.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.47.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.47.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.47.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.48.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.48.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.48.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.49.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.49.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.49.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.5.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.5.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.5.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.50.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.50.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.50.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.51.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.51.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.51.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.52.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.52.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.52.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.53.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.53.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.53.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.54.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.54.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.54.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.55.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.55.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.55.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.56.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.56.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.56.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.57.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.57.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.57.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.58.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.58.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.58.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.59.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.59.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.59.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.6.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.6.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.6.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.60.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.60.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.60.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.61.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.61.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.61.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.62.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.62.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.62.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.63.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.63.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.63.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.64.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.64.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.64.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.65.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.65.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.65.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.66.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.66.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.66.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.67.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.67.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.67.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.68.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.68.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.68.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.69.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.69.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.69.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.7.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.7.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.7.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.70.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.70.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.70.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.71.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.71.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.71.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.72.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.72.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.72.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.73.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.73.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.73.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.74.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.74.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.74.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.75.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.75.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.75.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.76.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.76.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.76.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.77.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.77.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.77.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.78.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.78.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.78.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.79.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.79.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.79.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.8.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.8.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.8.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.80.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.80.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.80.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.81.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.81.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.81.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.82.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.82.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.82.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.83.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.83.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.83.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.84.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.84.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.84.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.85.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.85.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.85.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.86.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.86.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.86.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.87.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.87.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.87.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.88.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.88.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.88.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.89.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.89.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.89.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.9.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.9.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.9.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.90.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.90.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.90.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.91.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.91.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.91.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.92.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.92.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.92.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.93.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.93.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.93.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.94.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.94.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.94.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.95.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.95.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.95.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.96.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.96.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.96.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.97.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.97.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.97.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.98.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.98.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.98.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.99.down_proj.weight": "model-00025-of-00049.safetensors", + "model.layers.25.mlp.experts.99.gate_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.experts.99.up_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.mlp.gate.weight": "model-00026-of-00049.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.input_layernorm.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.0.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.0.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.0.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.1.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.1.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.1.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.10.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.10.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.10.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.100.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.100.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.100.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.101.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.101.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.101.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.102.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.102.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.102.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.103.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.103.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.103.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.104.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.104.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.104.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.105.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.105.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.105.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.106.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.106.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.106.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.107.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.107.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.107.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.108.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.108.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.108.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.109.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.109.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.109.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.11.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.11.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.11.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.110.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.110.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.110.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.111.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.111.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.111.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.112.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.112.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.112.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.113.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.113.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.113.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.114.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.114.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.114.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.115.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.115.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.115.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.116.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.116.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.116.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.117.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.117.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.117.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.118.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.118.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.118.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.119.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.119.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.119.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.12.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.12.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.12.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.120.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.120.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.120.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.121.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.121.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.121.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.122.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.122.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.122.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.123.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.123.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.123.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.124.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.124.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.124.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.125.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.125.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.125.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.126.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.126.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.126.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.127.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.127.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.127.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.13.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.13.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.13.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.14.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.14.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.14.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.15.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.15.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.15.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.16.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.16.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.16.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.17.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.17.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.17.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.18.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.18.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.18.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.19.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.19.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.19.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.2.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.2.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.2.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.20.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.20.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.20.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.21.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.21.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.21.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.22.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.22.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.22.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.23.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.23.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.23.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.24.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.24.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.24.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.25.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.25.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.25.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.26.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.26.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.26.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.27.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.27.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.27.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.28.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.28.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.28.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.29.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.29.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.29.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.3.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.3.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.3.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.30.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.30.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.30.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.31.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.31.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.31.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.32.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.32.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.32.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.33.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.33.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.33.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.34.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.34.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.34.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.35.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.35.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.35.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.36.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.36.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.36.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.37.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.37.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.37.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.38.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.38.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.38.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.39.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.39.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.39.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.4.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.4.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.4.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.40.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.40.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.40.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.41.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.41.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.41.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.42.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.42.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.42.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.43.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.43.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.43.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.44.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.44.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.44.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.45.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.45.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.45.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.46.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.46.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.46.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.47.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.47.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.47.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.48.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.48.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.48.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.49.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.49.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.49.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.5.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.5.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.5.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.50.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.50.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.50.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.51.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.51.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.51.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.52.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.52.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.52.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.53.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.53.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.53.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.54.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.54.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.54.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.55.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.55.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.55.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.56.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.56.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.56.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.57.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.57.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.57.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.58.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.58.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.58.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.59.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.59.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.59.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.6.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.6.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.6.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.60.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.60.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.60.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.61.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.61.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.61.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.62.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.62.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.62.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.63.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.63.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.63.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.64.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.64.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.64.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.65.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.65.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.65.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.66.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.66.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.66.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.67.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.67.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.67.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.68.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.68.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.68.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.69.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.69.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.69.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.7.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.7.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.7.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.70.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.70.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.70.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.71.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.71.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.71.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.72.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.72.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.72.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.73.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.73.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.73.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.74.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.74.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.74.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.75.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.75.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.75.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.76.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.76.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.76.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.77.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.77.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.77.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.78.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.78.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.78.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.79.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.79.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.79.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.8.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.8.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.8.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.80.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.80.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.80.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.81.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.81.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.81.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.82.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.82.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.82.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.83.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.83.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.83.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.84.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.84.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.84.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.85.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.85.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.85.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.86.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.86.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.86.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.87.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.87.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.87.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.88.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.88.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.88.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.89.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.89.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.89.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.9.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.9.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.9.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.90.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.90.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.90.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.91.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.91.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.91.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.92.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.92.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.92.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.93.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.93.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.93.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.94.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.94.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.94.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.95.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.95.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.95.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.96.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.96.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.96.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.97.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.97.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.97.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.98.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.98.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.98.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.99.down_proj.weight": "model-00026-of-00049.safetensors", + "model.layers.26.mlp.experts.99.gate_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.experts.99.up_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.mlp.gate.weight": "model-00027-of-00049.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.input_layernorm.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.0.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.0.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.0.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.1.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.1.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.1.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.10.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.10.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.10.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.100.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.100.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.100.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.101.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.101.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.101.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.102.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.102.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.102.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.103.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.103.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.103.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.104.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.104.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.104.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.105.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.105.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.105.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.106.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.106.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.106.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.107.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.107.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.107.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.108.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.108.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.108.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.109.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.109.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.109.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.11.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.11.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.11.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.110.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.110.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.110.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.111.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.111.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.111.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.112.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.112.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.112.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.113.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.113.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.113.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.114.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.114.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.114.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.115.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.115.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.115.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.116.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.116.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.116.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.117.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.117.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.117.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.118.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.118.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.118.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.119.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.119.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.119.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.12.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.12.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.12.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.120.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.120.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.120.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.121.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.121.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.121.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.122.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.122.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.122.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.123.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.123.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.123.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.124.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.124.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.124.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.125.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.125.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.125.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.126.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.126.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.126.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.127.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.127.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.127.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.13.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.13.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.13.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.14.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.14.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.14.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.15.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.15.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.15.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.16.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.16.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.16.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.17.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.17.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.17.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.18.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.18.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.18.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.19.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.19.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.19.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.2.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.2.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.2.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.20.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.20.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.20.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.21.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.21.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.21.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.22.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.22.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.22.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.23.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.23.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.23.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.24.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.24.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.24.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.25.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.25.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.25.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.26.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.26.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.26.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.27.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.27.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.27.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.28.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.28.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.28.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.29.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.29.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.29.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.3.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.3.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.3.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.30.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.30.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.30.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.31.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.31.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.31.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.32.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.32.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.32.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.33.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.33.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.33.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.34.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.34.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.34.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.35.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.35.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.35.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.36.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.36.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.36.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.37.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.37.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.37.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.38.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.38.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.38.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.39.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.39.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.39.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.4.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.4.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.4.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.40.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.40.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.40.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.41.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.41.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.41.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.42.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.42.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.42.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.43.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.43.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.43.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.44.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.44.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.44.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.45.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.45.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.45.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.46.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.46.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.46.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.47.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.47.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.47.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.48.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.48.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.48.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.49.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.49.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.49.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.5.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.5.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.5.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.50.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.50.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.50.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.51.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.51.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.51.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.52.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.52.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.52.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.53.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.53.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.53.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.54.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.54.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.54.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.55.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.55.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.55.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.56.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.56.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.56.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.57.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.57.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.57.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.58.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.58.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.58.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.59.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.59.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.59.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.6.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.6.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.6.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.60.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.60.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.60.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.61.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.61.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.61.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.62.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.62.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.62.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.63.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.63.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.63.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.64.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.64.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.64.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.65.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.65.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.65.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.66.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.66.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.66.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.67.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.67.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.67.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.68.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.68.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.68.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.69.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.69.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.69.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.7.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.7.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.7.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.70.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.70.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.70.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.71.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.71.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.71.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.72.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.72.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.72.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.73.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.73.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.73.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.74.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.74.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.74.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.75.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.75.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.75.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.76.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.76.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.76.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.77.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.77.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.77.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.78.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.78.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.78.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.79.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.79.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.79.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.8.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.8.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.8.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.80.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.80.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.80.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.81.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.81.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.81.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.82.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.82.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.82.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.83.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.83.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.83.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.84.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.84.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.84.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.85.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.85.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.85.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.86.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.86.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.86.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.87.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.87.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.87.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.88.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.88.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.88.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.89.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.89.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.89.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.9.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.9.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.9.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.90.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.90.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.90.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.91.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.91.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.91.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.92.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.92.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.92.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.93.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.93.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.93.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.94.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.94.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.94.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.95.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.95.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.95.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.96.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.96.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.96.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.97.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.97.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.97.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.98.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.98.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.98.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.99.down_proj.weight": "model-00027-of-00049.safetensors", + "model.layers.27.mlp.experts.99.gate_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.experts.99.up_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.mlp.gate.weight": "model-00028-of-00049.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.input_layernorm.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.0.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.0.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.0.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.1.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.1.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.1.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.10.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.10.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.10.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.100.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.100.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.100.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.101.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.101.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.101.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.102.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.102.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.102.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.103.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.103.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.103.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.104.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.104.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.104.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.105.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.105.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.105.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.106.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.106.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.106.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.107.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.107.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.107.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.108.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.108.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.108.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.109.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.109.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.109.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.11.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.11.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.11.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.110.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.110.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.110.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.111.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.111.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.111.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.112.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.112.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.112.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.113.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.113.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.113.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.114.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.114.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.114.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.115.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.115.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.115.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.116.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.116.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.116.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.117.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.117.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.117.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.118.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.118.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.118.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.119.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.119.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.119.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.12.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.12.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.12.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.120.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.120.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.120.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.121.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.121.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.121.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.122.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.122.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.122.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.123.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.123.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.123.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.124.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.124.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.124.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.125.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.125.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.125.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.126.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.126.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.126.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.127.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.127.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.127.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.13.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.13.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.13.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.14.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.14.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.14.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.15.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.15.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.15.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.16.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.16.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.16.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.17.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.17.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.17.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.18.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.18.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.18.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.19.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.19.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.19.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.2.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.2.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.2.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.20.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.20.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.20.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.21.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.21.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.21.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.22.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.22.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.22.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.23.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.23.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.23.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.24.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.24.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.24.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.25.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.25.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.25.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.26.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.26.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.26.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.27.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.27.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.27.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.28.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.28.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.28.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.29.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.29.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.29.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.3.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.3.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.3.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.30.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.30.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.30.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.31.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.31.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.31.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.32.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.32.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.32.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.33.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.33.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.33.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.34.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.34.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.34.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.35.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.35.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.35.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.36.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.36.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.36.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.37.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.37.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.37.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.38.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.38.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.38.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.39.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.39.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.39.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.4.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.4.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.4.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.40.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.40.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.40.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.41.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.41.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.41.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.42.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.42.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.42.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.43.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.43.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.43.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.44.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.44.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.44.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.45.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.45.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.45.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.46.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.46.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.46.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.47.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.47.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.47.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.48.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.48.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.48.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.49.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.49.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.49.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.5.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.5.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.5.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.50.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.50.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.50.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.51.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.51.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.51.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.52.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.52.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.52.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.53.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.53.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.53.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.54.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.54.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.54.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.55.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.55.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.55.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.56.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.56.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.56.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.57.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.57.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.57.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.58.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.58.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.58.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.59.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.59.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.59.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.6.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.6.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.6.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.60.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.60.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.60.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.61.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.61.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.61.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.62.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.62.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.62.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.63.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.63.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.63.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.64.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.64.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.64.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.65.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.65.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.65.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.66.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.66.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.66.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.67.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.67.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.67.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.68.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.68.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.68.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.69.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.69.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.69.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.7.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.7.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.7.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.70.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.70.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.70.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.71.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.71.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.71.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.72.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.72.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.72.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.73.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.73.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.73.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.74.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.74.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.74.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.75.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.75.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.75.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.76.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.76.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.76.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.77.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.77.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.77.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.78.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.78.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.78.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.79.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.79.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.79.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.8.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.8.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.8.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.80.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.80.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.80.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.81.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.81.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.81.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.82.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.82.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.82.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.83.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.83.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.83.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.84.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.84.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.84.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.85.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.85.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.85.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.86.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.86.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.86.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.87.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.87.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.87.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.88.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.88.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.88.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.89.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.89.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.89.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.9.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.9.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.9.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.90.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.90.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.90.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.91.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.91.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.91.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.92.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.92.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.92.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.93.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.93.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.93.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.94.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.94.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.94.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.95.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.95.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.95.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.96.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.96.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.96.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.97.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.97.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.97.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.98.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.98.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.98.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.99.down_proj.weight": "model-00028-of-00049.safetensors", + "model.layers.28.mlp.experts.99.gate_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.experts.99.up_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.mlp.gate.weight": "model-00029-of-00049.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.input_layernorm.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.0.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.0.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.0.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.1.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.1.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.1.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.10.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.10.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.10.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.100.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.100.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.100.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.101.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.101.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.101.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.102.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.102.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.102.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.103.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.103.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.103.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.104.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.104.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.104.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.105.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.105.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.105.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.106.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.106.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.106.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.107.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.107.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.107.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.108.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.108.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.108.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.109.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.109.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.109.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.11.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.11.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.11.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.110.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.110.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.110.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.111.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.111.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.111.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.112.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.112.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.112.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.113.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.113.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.113.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.114.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.114.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.114.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.115.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.115.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.115.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.116.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.116.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.116.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.117.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.117.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.117.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.118.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.118.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.118.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.119.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.119.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.119.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.12.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.12.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.12.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.120.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.120.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.120.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.121.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.121.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.121.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.122.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.122.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.122.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.123.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.123.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.123.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.124.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.124.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.124.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.125.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.125.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.125.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.126.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.126.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.126.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.127.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.127.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.127.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.13.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.13.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.13.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.14.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.14.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.14.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.15.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.15.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.15.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.16.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.16.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.16.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.17.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.17.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.17.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.18.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.18.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.18.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.19.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.19.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.19.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.2.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.2.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.2.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.20.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.20.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.20.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.21.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.21.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.21.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.22.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.22.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.22.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.23.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.23.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.23.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.24.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.24.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.24.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.25.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.25.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.25.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.26.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.26.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.26.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.27.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.27.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.27.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.28.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.28.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.28.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.29.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.29.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.29.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.3.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.3.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.3.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.30.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.30.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.30.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.31.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.31.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.31.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.32.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.32.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.32.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.33.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.33.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.33.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.34.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.34.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.34.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.35.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.35.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.35.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.36.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.36.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.36.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.37.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.37.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.37.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.38.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.38.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.38.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.39.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.39.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.39.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.4.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.4.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.4.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.40.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.40.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.40.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.41.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.41.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.41.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.42.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.42.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.42.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.43.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.43.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.43.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.44.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.44.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.44.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.45.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.45.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.45.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.46.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.46.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.46.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.47.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.47.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.47.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.48.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.48.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.48.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.49.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.49.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.49.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.5.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.5.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.5.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.50.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.50.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.50.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.51.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.51.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.51.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.52.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.52.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.52.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.53.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.53.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.53.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.54.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.54.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.54.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.55.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.55.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.55.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.56.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.56.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.56.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.57.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.57.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.57.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.58.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.58.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.58.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.59.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.59.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.59.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.6.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.6.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.6.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.60.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.60.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.60.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.61.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.61.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.61.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.62.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.62.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.62.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.63.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.63.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.63.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.64.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.64.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.64.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.65.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.65.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.65.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.66.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.66.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.66.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.67.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.67.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.67.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.68.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.68.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.68.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.69.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.69.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.69.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.7.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.7.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.7.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.70.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.70.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.70.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.71.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.71.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.71.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.72.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.72.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.72.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.73.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.73.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.73.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.74.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.74.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.74.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.75.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.75.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.75.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.76.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.76.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.76.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.77.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.77.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.77.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.78.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.78.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.78.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.79.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.79.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.79.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.8.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.8.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.8.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.80.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.80.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.80.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.81.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.81.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.81.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.82.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.82.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.82.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.83.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.83.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.83.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.84.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.84.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.84.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.85.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.85.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.85.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.86.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.86.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.86.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.87.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.87.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.87.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.88.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.88.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.88.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.89.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.89.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.89.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.9.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.9.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.9.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.90.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.90.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.90.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.91.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.91.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.91.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.92.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.92.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.92.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.93.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.93.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.93.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.94.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.94.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.94.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.95.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.95.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.95.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.96.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.96.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.96.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.97.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.97.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.97.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.98.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.98.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.98.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.99.down_proj.weight": "model-00029-of-00049.safetensors", + "model.layers.29.mlp.experts.99.gate_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.experts.99.up_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.mlp.gate.weight": "model-00030-of-00049.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.3.input_layernorm.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.0.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.0.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.1.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.1.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.10.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.10.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.10.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.100.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.100.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.100.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.101.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.101.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.101.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.102.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.102.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.102.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.103.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.103.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.103.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.104.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.104.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.104.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.105.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.105.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.105.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.106.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.106.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.106.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.107.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.107.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.107.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.108.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.108.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.108.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.109.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.109.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.109.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.11.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.11.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.11.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.110.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.110.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.110.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.111.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.111.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.111.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.112.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.112.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.112.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.113.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.113.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.113.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.114.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.114.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.114.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.115.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.115.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.115.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.116.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.116.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.116.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.117.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.117.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.117.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.118.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.118.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.118.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.119.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.119.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.119.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.12.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.12.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.12.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.120.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.120.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.120.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.121.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.121.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.121.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.122.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.122.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.122.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.123.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.123.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.123.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.124.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.124.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.124.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.125.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.125.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.125.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.126.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.126.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.126.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.127.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.127.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.127.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.13.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.13.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.13.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.14.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.14.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.14.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.15.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.15.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.15.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.16.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.16.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.16.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.17.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.17.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.17.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.18.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.18.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.18.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.19.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.19.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.19.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.2.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.2.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.2.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.20.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.20.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.20.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.21.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.21.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.21.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.22.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.22.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.22.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.23.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.23.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.23.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.24.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.24.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.24.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.25.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.25.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.25.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.26.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.26.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.26.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.27.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.27.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.27.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.28.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.28.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.28.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.29.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.29.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.29.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.3.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.3.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.3.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.30.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.30.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.30.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.31.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.31.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.31.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.32.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.32.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.32.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.33.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.33.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.33.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.34.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.34.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.34.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.35.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.35.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.35.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.36.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.36.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.36.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.37.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.37.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.37.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.38.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.38.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.38.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.39.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.39.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.39.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.4.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.4.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.4.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.40.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.40.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.40.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.41.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.41.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.41.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.42.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.42.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.42.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.43.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.43.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.43.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.44.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.44.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.44.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.45.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.45.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.45.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.46.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.46.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.46.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.47.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.47.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.47.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.48.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.48.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.48.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.49.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.49.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.49.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.5.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.5.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.5.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.50.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.50.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.50.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.51.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.51.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.51.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.52.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.52.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.52.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.53.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.53.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.53.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.54.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.54.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.54.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.55.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.55.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.55.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.56.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.56.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.56.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.57.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.57.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.57.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.58.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.58.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.58.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.59.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.59.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.59.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.6.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.6.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.6.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.60.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.60.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.60.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.61.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.61.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.61.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.62.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.62.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.62.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.63.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.63.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.63.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.64.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.64.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.64.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.65.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.65.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.65.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.66.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.66.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.66.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.67.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.67.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.67.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.68.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.68.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.68.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.69.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.69.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.69.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.7.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.7.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.7.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.70.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.70.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.70.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.71.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.71.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.71.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.72.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.72.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.72.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.73.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.73.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.73.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.74.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.74.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.74.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.75.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.75.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.75.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.76.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.76.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.76.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.77.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.77.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.77.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.78.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.78.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.78.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.79.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.79.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.79.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.8.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.8.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.8.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.80.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.80.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.80.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.81.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.81.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.81.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.82.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.82.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.82.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.83.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.83.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.83.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.84.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.84.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.84.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.85.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.85.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.85.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.86.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.86.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.86.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.87.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.87.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.87.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.88.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.88.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.88.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.89.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.89.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.89.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.9.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.9.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.9.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.90.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.90.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.90.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.91.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.91.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.91.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.92.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.92.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.92.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.93.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.93.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.93.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.94.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.94.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.94.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.95.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.95.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.95.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.96.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.96.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.96.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.97.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.97.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.97.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.98.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.98.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.98.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.99.down_proj.weight": "model-00003-of-00049.safetensors", + "model.layers.3.mlp.experts.99.gate_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.experts.99.up_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.mlp.gate.weight": "model-00004-of-00049.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.30.input_layernorm.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.0.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.0.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.0.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.1.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.1.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.1.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.10.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.10.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.10.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.100.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.100.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.100.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.101.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.101.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.101.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.102.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.102.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.102.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.103.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.103.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.103.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.104.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.104.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.104.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.105.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.105.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.105.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.106.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.106.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.106.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.107.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.107.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.107.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.108.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.108.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.108.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.109.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.109.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.109.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.11.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.11.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.11.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.110.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.110.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.110.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.111.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.111.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.111.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.112.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.112.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.112.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.113.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.113.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.113.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.114.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.114.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.114.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.115.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.115.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.115.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.116.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.116.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.116.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.117.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.117.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.117.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.118.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.118.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.118.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.119.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.119.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.119.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.12.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.12.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.12.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.120.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.120.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.120.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.121.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.121.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.121.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.122.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.122.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.122.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.123.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.123.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.123.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.124.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.124.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.124.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.125.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.125.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.125.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.126.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.126.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.126.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.127.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.127.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.127.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.13.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.13.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.13.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.14.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.14.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.14.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.15.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.15.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.15.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.16.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.16.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.16.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.17.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.17.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.17.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.18.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.18.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.18.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.19.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.19.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.19.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.2.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.2.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.2.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.20.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.20.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.20.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.21.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.21.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.21.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.22.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.22.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.22.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.23.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.23.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.23.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.24.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.24.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.24.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.25.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.25.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.25.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.26.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.26.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.26.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.27.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.27.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.27.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.28.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.28.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.28.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.29.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.29.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.29.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.3.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.3.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.3.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.30.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.30.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.30.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.31.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.31.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.31.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.32.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.32.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.32.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.33.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.33.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.33.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.34.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.34.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.34.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.35.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.35.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.35.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.36.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.36.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.36.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.37.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.37.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.37.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.38.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.38.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.38.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.39.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.39.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.39.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.4.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.4.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.4.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.40.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.40.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.40.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.41.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.41.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.41.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.42.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.42.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.42.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.43.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.43.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.43.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.44.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.44.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.44.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.45.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.45.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.45.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.46.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.46.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.46.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.47.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.47.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.47.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.48.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.48.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.48.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.49.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.49.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.49.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.5.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.5.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.5.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.50.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.50.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.50.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.51.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.51.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.51.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.52.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.52.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.52.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.53.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.53.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.53.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.54.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.54.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.54.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.55.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.55.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.55.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.56.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.56.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.56.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.57.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.57.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.57.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.58.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.58.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.58.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.59.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.59.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.59.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.6.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.6.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.6.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.60.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.60.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.60.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.61.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.61.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.61.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.62.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.62.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.62.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.63.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.63.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.63.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.64.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.64.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.64.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.65.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.65.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.65.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.66.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.66.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.66.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.67.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.67.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.67.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.68.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.68.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.68.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.69.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.69.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.69.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.7.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.7.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.7.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.70.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.70.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.70.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.71.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.71.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.71.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.72.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.72.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.72.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.73.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.73.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.73.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.74.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.74.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.74.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.75.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.75.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.75.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.76.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.76.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.76.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.77.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.77.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.77.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.78.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.78.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.78.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.79.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.79.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.79.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.8.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.8.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.8.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.80.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.80.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.80.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.81.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.81.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.81.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.82.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.82.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.82.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.83.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.83.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.83.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.84.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.84.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.84.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.85.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.85.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.85.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.86.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.86.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.86.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.87.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.87.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.87.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.88.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.88.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.88.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.89.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.89.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.89.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.9.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.9.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.9.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.90.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.90.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.90.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.91.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.91.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.91.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.92.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.92.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.92.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.93.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.93.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.93.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.94.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.94.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.94.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.95.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.95.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.95.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.96.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.96.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.96.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.97.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.97.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.97.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.98.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.98.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.98.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.99.down_proj.weight": "model-00030-of-00049.safetensors", + "model.layers.30.mlp.experts.99.gate_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.experts.99.up_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.mlp.gate.weight": "model-00031-of-00049.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.input_layernorm.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.0.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.0.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.0.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.1.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.1.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.1.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.10.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.10.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.10.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.100.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.100.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.100.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.101.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.101.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.101.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.102.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.102.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.102.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.103.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.103.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.103.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.104.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.104.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.104.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.105.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.105.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.105.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.106.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.106.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.106.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.107.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.107.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.107.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.108.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.108.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.108.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.109.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.109.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.109.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.11.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.11.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.11.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.110.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.110.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.110.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.111.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.111.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.111.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.112.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.112.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.112.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.113.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.113.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.113.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.114.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.114.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.114.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.115.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.115.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.115.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.116.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.116.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.116.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.117.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.117.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.117.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.118.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.118.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.118.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.119.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.119.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.119.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.12.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.12.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.12.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.120.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.120.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.120.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.121.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.121.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.121.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.122.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.122.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.122.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.123.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.123.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.123.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.124.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.124.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.124.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.125.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.125.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.125.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.126.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.126.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.126.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.127.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.127.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.127.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.13.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.13.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.13.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.14.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.14.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.14.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.15.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.15.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.15.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.16.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.16.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.16.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.17.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.17.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.17.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.18.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.18.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.18.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.19.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.19.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.19.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.2.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.2.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.2.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.20.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.20.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.20.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.21.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.21.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.21.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.22.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.22.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.22.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.23.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.23.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.23.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.24.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.24.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.24.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.25.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.25.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.25.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.26.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.26.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.26.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.27.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.27.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.27.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.28.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.28.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.28.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.29.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.29.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.29.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.3.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.3.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.3.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.30.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.30.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.30.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.31.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.31.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.31.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.32.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.32.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.32.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.33.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.33.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.33.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.34.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.34.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.34.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.35.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.35.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.35.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.36.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.36.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.36.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.37.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.37.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.37.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.38.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.38.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.38.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.39.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.39.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.39.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.4.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.4.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.4.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.40.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.40.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.40.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.41.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.41.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.41.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.42.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.42.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.42.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.43.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.43.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.43.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.44.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.44.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.44.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.45.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.45.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.45.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.46.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.46.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.46.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.47.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.47.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.47.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.48.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.48.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.48.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.49.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.49.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.49.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.5.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.5.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.5.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.50.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.50.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.50.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.51.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.51.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.51.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.52.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.52.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.52.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.53.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.53.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.53.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.54.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.54.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.54.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.55.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.55.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.55.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.56.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.56.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.56.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.57.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.57.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.57.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.58.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.58.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.58.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.59.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.59.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.59.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.6.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.6.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.6.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.60.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.60.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.60.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.61.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.61.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.61.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.62.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.62.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.62.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.63.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.63.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.63.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.64.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.64.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.64.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.65.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.65.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.65.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.66.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.66.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.66.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.67.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.67.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.67.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.68.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.68.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.68.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.69.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.69.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.69.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.7.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.7.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.7.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.70.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.70.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.70.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.71.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.71.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.71.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.72.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.72.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.72.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.73.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.73.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.73.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.74.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.74.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.74.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.75.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.75.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.75.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.76.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.76.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.76.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.77.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.77.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.77.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.78.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.78.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.78.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.79.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.79.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.79.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.8.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.8.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.8.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.80.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.80.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.80.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.81.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.81.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.81.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.82.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.82.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.82.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.83.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.83.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.83.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.84.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.84.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.84.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.85.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.85.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.85.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.86.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.86.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.86.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.87.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.87.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.87.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.88.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.88.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.88.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.89.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.89.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.89.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.9.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.9.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.9.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.90.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.90.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.90.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.91.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.91.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.91.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.92.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.92.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.92.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.93.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.93.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.93.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.94.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.94.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.94.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.95.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.95.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.95.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.96.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.96.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.96.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.97.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.97.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.97.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.98.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.98.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.98.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.99.down_proj.weight": "model-00031-of-00049.safetensors", + "model.layers.31.mlp.experts.99.gate_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.experts.99.up_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.mlp.gate.weight": "model-00032-of-00049.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.input_layernorm.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.0.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.0.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.0.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.1.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.1.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.1.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.10.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.10.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.10.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.100.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.100.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.100.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.101.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.101.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.101.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.102.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.102.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.102.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.103.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.103.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.103.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.104.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.104.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.104.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.105.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.105.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.105.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.106.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.106.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.106.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.107.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.107.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.107.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.108.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.108.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.108.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.109.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.109.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.109.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.11.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.11.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.11.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.110.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.110.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.110.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.111.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.111.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.111.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.112.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.112.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.112.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.113.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.113.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.113.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.114.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.114.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.114.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.115.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.115.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.115.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.116.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.116.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.116.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.117.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.117.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.117.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.118.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.118.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.118.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.119.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.119.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.119.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.12.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.12.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.12.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.120.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.120.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.120.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.121.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.121.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.121.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.122.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.122.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.122.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.123.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.123.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.123.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.124.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.124.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.124.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.125.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.125.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.125.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.126.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.126.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.126.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.127.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.127.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.127.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.13.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.13.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.13.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.14.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.14.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.14.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.15.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.15.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.15.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.16.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.16.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.16.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.17.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.17.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.17.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.18.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.18.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.18.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.19.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.19.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.19.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.2.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.2.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.2.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.20.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.20.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.20.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.21.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.21.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.21.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.22.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.22.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.22.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.23.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.23.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.23.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.24.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.24.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.24.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.25.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.25.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.25.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.26.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.26.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.26.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.27.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.27.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.27.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.28.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.28.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.28.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.29.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.29.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.29.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.3.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.3.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.3.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.30.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.30.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.30.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.31.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.31.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.31.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.32.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.32.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.32.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.33.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.33.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.33.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.34.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.34.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.34.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.35.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.35.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.35.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.36.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.36.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.36.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.37.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.37.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.37.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.38.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.38.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.38.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.39.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.39.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.39.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.4.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.4.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.4.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.40.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.40.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.40.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.41.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.41.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.41.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.42.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.42.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.42.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.43.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.43.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.43.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.44.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.44.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.44.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.45.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.45.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.45.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.46.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.46.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.46.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.47.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.47.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.47.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.48.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.48.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.48.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.49.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.49.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.49.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.5.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.5.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.5.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.50.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.50.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.50.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.51.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.51.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.51.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.52.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.52.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.52.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.53.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.53.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.53.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.54.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.54.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.54.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.55.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.55.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.55.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.56.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.56.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.56.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.57.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.57.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.57.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.58.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.58.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.58.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.59.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.59.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.59.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.6.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.6.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.6.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.60.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.60.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.60.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.61.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.61.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.61.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.62.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.62.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.62.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.63.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.63.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.63.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.64.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.64.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.64.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.65.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.65.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.65.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.66.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.66.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.66.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.67.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.67.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.67.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.68.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.68.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.68.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.69.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.69.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.69.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.7.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.7.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.7.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.70.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.70.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.70.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.71.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.71.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.71.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.72.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.72.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.72.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.73.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.73.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.73.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.74.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.74.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.74.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.75.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.75.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.75.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.76.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.76.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.76.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.77.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.77.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.77.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.78.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.78.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.78.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.79.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.79.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.79.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.8.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.8.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.8.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.80.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.80.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.80.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.81.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.81.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.81.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.82.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.82.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.82.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.83.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.83.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.83.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.84.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.84.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.84.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.85.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.85.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.85.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.86.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.86.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.86.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.87.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.87.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.87.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.88.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.88.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.88.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.89.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.89.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.89.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.9.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.9.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.9.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.90.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.90.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.90.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.91.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.91.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.91.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.92.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.92.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.92.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.93.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.93.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.93.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.94.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.94.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.94.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.95.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.95.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.95.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.96.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.96.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.96.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.97.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.97.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.97.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.98.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.98.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.98.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.99.down_proj.weight": "model-00032-of-00049.safetensors", + "model.layers.32.mlp.experts.99.gate_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.experts.99.up_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.mlp.gate.weight": "model-00033-of-00049.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.input_layernorm.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.0.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.0.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.0.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.1.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.1.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.1.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.10.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.10.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.10.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.100.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.100.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.100.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.101.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.101.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.101.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.102.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.102.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.102.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.103.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.103.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.103.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.104.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.104.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.104.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.105.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.105.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.105.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.106.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.106.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.106.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.107.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.107.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.107.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.108.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.108.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.108.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.109.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.109.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.109.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.11.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.11.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.11.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.110.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.110.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.110.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.111.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.111.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.111.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.112.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.112.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.112.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.113.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.113.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.113.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.114.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.114.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.114.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.115.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.115.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.115.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.116.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.116.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.116.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.117.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.117.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.117.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.118.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.118.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.118.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.119.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.119.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.119.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.12.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.12.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.12.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.120.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.120.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.120.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.121.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.121.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.121.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.122.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.122.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.122.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.123.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.123.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.123.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.124.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.124.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.124.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.125.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.125.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.125.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.126.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.126.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.126.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.127.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.127.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.127.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.13.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.13.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.13.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.14.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.14.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.14.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.15.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.15.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.15.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.16.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.16.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.16.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.17.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.17.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.17.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.18.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.18.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.18.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.19.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.19.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.19.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.2.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.2.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.2.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.20.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.20.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.20.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.21.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.21.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.21.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.22.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.22.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.22.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.23.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.23.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.23.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.24.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.24.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.24.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.25.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.25.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.25.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.26.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.26.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.26.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.27.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.27.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.27.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.28.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.28.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.28.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.29.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.29.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.29.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.3.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.3.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.3.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.30.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.30.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.30.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.31.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.31.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.31.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.32.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.32.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.32.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.33.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.33.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.33.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.34.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.34.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.34.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.35.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.35.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.35.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.36.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.36.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.36.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.37.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.37.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.37.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.38.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.38.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.38.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.39.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.39.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.39.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.4.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.4.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.4.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.40.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.40.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.40.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.41.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.41.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.41.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.42.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.42.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.42.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.43.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.43.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.43.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.44.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.44.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.44.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.45.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.45.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.45.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.46.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.46.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.46.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.47.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.47.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.47.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.48.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.48.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.48.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.49.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.49.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.49.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.5.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.5.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.5.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.50.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.50.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.50.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.51.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.51.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.51.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.52.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.52.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.52.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.53.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.53.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.53.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.54.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.54.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.54.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.55.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.55.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.55.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.56.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.56.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.56.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.57.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.57.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.57.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.58.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.58.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.58.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.59.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.59.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.59.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.6.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.6.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.6.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.60.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.60.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.60.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.61.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.61.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.61.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.62.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.62.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.62.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.63.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.63.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.63.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.64.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.64.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.64.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.65.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.65.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.65.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.66.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.66.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.66.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.67.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.67.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.67.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.68.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.68.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.68.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.69.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.69.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.69.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.7.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.7.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.7.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.70.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.70.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.70.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.71.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.71.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.71.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.72.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.72.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.72.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.73.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.73.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.73.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.74.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.74.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.74.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.75.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.75.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.75.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.76.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.76.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.76.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.77.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.77.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.77.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.78.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.78.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.78.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.79.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.79.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.79.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.8.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.8.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.8.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.80.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.80.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.80.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.81.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.81.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.81.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.82.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.82.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.82.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.83.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.83.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.83.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.84.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.84.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.84.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.85.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.85.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.85.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.86.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.86.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.86.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.87.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.87.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.87.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.88.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.88.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.88.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.89.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.89.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.89.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.9.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.9.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.9.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.90.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.90.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.90.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.91.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.91.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.91.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.92.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.92.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.92.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.93.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.93.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.93.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.94.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.94.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.94.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.95.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.95.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.95.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.96.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.96.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.96.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.97.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.97.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.97.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.98.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.98.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.98.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.99.down_proj.weight": "model-00033-of-00049.safetensors", + "model.layers.33.mlp.experts.99.gate_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.experts.99.up_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.mlp.gate.weight": "model-00034-of-00049.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.input_layernorm.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.0.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.0.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.0.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.1.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.1.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.1.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.10.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.10.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.10.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.100.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.100.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.100.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.101.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.101.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.101.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.102.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.102.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.102.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.103.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.103.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.103.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.104.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.104.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.104.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.105.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.105.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.105.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.106.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.106.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.106.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.107.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.107.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.107.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.108.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.108.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.108.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.109.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.109.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.109.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.11.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.11.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.11.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.110.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.110.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.110.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.111.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.111.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.111.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.112.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.112.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.112.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.113.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.113.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.113.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.114.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.114.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.114.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.115.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.115.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.115.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.116.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.116.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.116.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.117.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.117.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.117.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.118.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.118.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.118.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.119.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.119.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.119.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.12.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.12.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.12.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.120.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.120.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.120.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.121.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.121.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.121.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.122.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.122.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.122.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.123.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.123.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.123.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.124.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.124.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.124.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.125.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.125.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.125.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.126.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.126.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.126.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.127.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.127.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.127.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.13.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.13.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.13.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.14.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.14.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.14.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.15.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.15.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.15.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.16.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.16.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.16.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.17.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.17.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.17.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.18.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.18.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.18.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.19.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.19.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.19.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.2.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.2.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.2.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.20.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.20.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.20.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.21.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.21.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.21.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.22.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.22.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.22.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.23.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.23.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.23.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.24.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.24.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.24.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.25.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.25.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.25.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.26.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.26.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.26.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.27.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.27.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.27.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.28.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.28.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.28.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.29.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.29.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.29.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.3.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.3.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.3.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.30.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.30.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.30.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.31.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.31.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.31.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.32.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.32.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.32.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.33.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.33.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.33.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.34.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.34.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.34.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.35.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.35.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.35.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.36.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.36.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.36.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.37.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.37.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.37.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.38.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.38.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.38.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.39.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.39.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.39.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.4.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.4.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.4.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.40.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.40.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.40.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.41.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.41.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.41.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.42.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.42.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.42.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.43.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.43.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.43.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.44.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.44.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.44.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.45.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.45.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.45.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.46.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.46.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.46.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.47.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.47.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.47.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.48.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.48.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.48.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.49.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.49.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.49.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.5.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.5.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.5.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.50.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.50.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.50.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.51.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.51.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.51.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.52.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.52.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.52.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.53.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.53.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.53.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.54.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.54.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.54.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.55.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.55.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.55.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.56.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.56.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.56.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.57.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.57.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.57.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.58.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.58.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.58.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.59.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.59.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.59.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.6.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.6.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.6.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.60.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.60.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.60.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.61.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.61.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.61.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.62.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.62.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.62.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.63.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.63.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.63.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.64.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.64.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.64.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.65.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.65.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.65.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.66.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.66.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.66.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.67.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.67.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.67.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.68.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.68.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.68.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.69.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.69.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.69.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.7.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.7.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.7.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.70.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.70.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.70.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.71.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.71.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.71.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.72.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.72.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.72.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.73.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.73.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.73.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.74.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.74.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.74.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.75.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.75.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.75.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.76.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.76.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.76.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.77.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.77.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.77.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.78.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.78.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.78.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.79.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.79.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.79.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.8.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.8.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.8.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.80.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.80.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.80.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.81.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.81.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.81.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.82.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.82.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.82.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.83.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.83.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.83.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.84.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.84.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.84.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.85.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.85.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.85.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.86.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.86.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.86.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.87.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.87.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.87.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.88.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.88.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.88.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.89.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.89.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.89.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.9.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.9.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.9.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.90.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.90.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.90.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.91.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.91.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.91.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.92.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.92.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.92.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.93.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.93.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.93.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.94.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.94.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.94.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.95.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.95.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.95.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.96.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.96.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.96.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.97.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.97.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.97.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.98.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.98.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.98.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.99.down_proj.weight": "model-00034-of-00049.safetensors", + "model.layers.34.mlp.experts.99.gate_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.experts.99.up_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.mlp.gate.weight": "model-00035-of-00049.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.input_layernorm.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.0.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.0.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.0.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.1.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.1.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.1.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.10.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.10.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.10.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.100.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.100.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.100.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.101.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.101.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.101.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.102.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.102.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.102.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.103.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.103.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.103.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.104.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.104.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.104.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.105.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.105.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.105.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.106.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.106.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.106.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.107.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.107.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.107.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.108.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.108.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.108.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.109.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.109.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.109.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.11.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.11.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.11.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.110.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.110.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.110.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.111.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.111.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.111.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.112.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.112.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.112.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.113.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.113.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.113.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.114.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.114.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.114.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.115.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.115.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.115.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.116.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.116.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.116.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.117.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.117.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.117.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.118.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.118.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.118.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.119.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.119.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.119.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.12.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.12.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.12.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.120.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.120.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.120.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.121.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.121.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.121.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.122.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.122.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.122.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.123.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.123.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.123.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.124.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.124.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.124.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.125.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.125.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.125.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.126.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.126.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.126.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.127.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.127.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.127.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.13.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.13.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.13.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.14.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.14.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.14.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.15.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.15.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.15.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.16.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.16.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.16.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.17.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.17.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.17.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.18.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.18.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.18.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.19.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.19.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.19.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.2.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.2.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.2.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.20.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.20.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.20.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.21.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.21.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.21.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.22.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.22.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.22.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.23.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.23.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.23.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.24.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.24.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.24.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.25.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.25.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.25.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.26.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.26.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.26.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.27.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.27.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.27.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.28.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.28.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.28.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.29.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.29.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.29.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.3.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.3.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.3.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.30.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.30.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.30.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.31.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.31.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.31.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.32.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.32.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.32.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.33.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.33.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.33.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.34.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.34.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.34.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.35.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.35.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.35.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.36.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.36.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.36.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.37.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.37.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.37.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.38.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.38.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.38.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.39.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.39.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.39.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.4.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.4.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.4.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.40.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.40.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.40.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.41.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.41.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.41.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.42.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.42.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.42.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.43.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.43.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.43.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.44.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.44.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.44.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.45.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.45.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.45.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.46.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.46.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.46.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.47.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.47.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.47.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.48.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.48.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.48.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.49.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.49.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.49.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.5.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.5.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.5.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.50.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.50.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.50.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.51.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.51.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.51.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.52.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.52.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.52.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.53.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.53.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.53.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.54.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.54.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.54.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.55.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.55.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.55.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.56.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.56.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.56.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.57.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.57.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.57.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.58.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.58.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.58.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.59.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.59.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.59.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.6.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.6.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.6.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.60.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.60.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.60.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.61.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.61.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.61.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.62.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.62.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.62.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.63.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.63.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.63.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.64.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.64.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.64.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.65.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.65.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.65.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.66.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.66.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.66.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.67.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.67.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.67.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.68.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.68.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.68.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.69.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.69.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.69.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.7.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.7.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.7.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.70.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.70.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.70.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.71.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.71.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.71.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.72.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.72.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.72.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.73.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.73.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.73.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.74.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.74.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.74.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.75.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.75.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.75.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.76.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.76.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.76.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.77.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.77.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.77.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.78.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.78.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.78.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.79.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.79.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.79.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.8.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.8.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.8.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.80.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.80.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.80.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.81.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.81.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.81.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.82.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.82.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.82.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.83.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.83.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.83.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.84.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.84.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.84.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.85.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.85.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.85.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.86.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.86.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.86.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.87.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.87.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.87.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.88.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.88.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.88.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.89.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.89.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.89.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.9.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.9.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.9.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.90.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.90.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.90.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.91.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.91.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.91.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.92.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.92.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.92.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.93.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.93.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.93.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.94.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.94.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.94.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.95.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.95.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.95.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.96.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.96.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.96.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.97.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.97.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.97.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.98.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.98.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.98.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.99.down_proj.weight": "model-00035-of-00049.safetensors", + "model.layers.35.mlp.experts.99.gate_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.experts.99.up_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.mlp.gate.weight": "model-00036-of-00049.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.input_layernorm.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.0.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.0.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.0.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.1.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.1.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.1.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.10.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.10.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.10.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.100.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.100.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.100.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.101.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.101.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.101.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.102.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.102.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.102.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.103.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.103.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.103.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.104.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.104.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.104.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.105.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.105.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.105.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.106.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.106.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.106.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.107.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.107.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.107.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.108.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.108.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.108.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.109.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.109.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.109.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.11.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.11.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.11.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.110.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.110.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.110.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.111.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.111.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.111.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.112.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.112.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.112.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.113.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.113.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.113.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.114.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.114.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.114.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.115.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.115.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.115.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.116.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.116.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.116.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.117.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.117.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.117.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.118.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.118.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.118.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.119.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.119.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.119.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.12.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.12.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.12.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.120.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.120.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.120.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.121.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.121.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.121.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.122.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.122.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.122.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.123.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.123.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.123.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.124.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.124.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.124.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.125.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.125.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.125.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.126.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.126.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.126.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.127.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.127.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.127.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.13.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.13.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.13.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.14.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.14.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.14.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.15.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.15.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.15.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.16.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.16.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.16.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.17.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.17.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.17.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.18.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.18.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.18.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.19.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.19.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.19.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.2.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.2.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.2.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.20.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.20.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.20.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.21.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.21.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.21.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.22.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.22.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.22.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.23.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.23.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.23.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.24.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.24.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.24.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.25.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.25.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.25.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.26.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.26.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.26.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.27.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.27.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.27.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.28.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.28.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.28.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.29.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.29.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.29.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.3.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.3.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.3.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.30.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.30.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.30.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.31.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.31.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.31.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.32.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.32.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.32.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.33.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.33.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.33.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.34.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.34.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.34.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.35.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.35.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.35.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.36.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.36.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.36.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.37.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.37.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.37.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.38.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.38.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.38.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.39.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.39.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.39.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.4.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.4.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.4.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.40.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.40.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.40.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.41.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.41.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.41.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.42.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.42.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.42.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.43.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.43.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.43.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.44.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.44.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.44.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.45.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.45.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.45.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.46.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.46.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.46.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.47.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.47.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.47.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.48.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.48.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.48.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.49.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.49.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.49.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.5.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.5.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.5.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.50.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.50.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.50.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.51.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.51.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.51.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.52.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.52.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.52.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.53.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.53.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.53.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.54.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.54.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.54.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.55.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.55.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.55.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.56.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.56.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.56.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.57.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.57.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.57.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.58.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.58.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.58.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.59.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.59.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.59.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.6.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.6.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.6.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.60.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.60.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.60.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.61.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.61.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.61.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.62.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.62.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.62.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.63.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.63.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.63.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.64.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.64.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.64.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.65.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.65.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.65.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.66.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.66.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.66.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.67.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.67.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.67.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.68.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.68.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.68.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.69.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.69.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.69.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.7.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.7.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.7.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.70.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.70.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.70.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.71.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.71.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.71.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.72.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.72.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.72.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.73.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.73.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.73.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.74.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.74.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.74.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.75.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.75.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.75.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.76.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.76.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.76.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.77.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.77.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.77.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.78.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.78.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.78.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.79.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.79.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.79.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.8.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.8.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.8.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.80.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.80.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.80.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.81.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.81.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.81.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.82.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.82.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.82.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.83.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.83.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.83.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.84.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.84.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.84.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.85.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.85.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.85.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.86.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.86.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.86.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.87.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.87.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.87.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.88.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.88.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.88.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.89.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.89.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.89.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.9.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.9.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.9.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.90.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.90.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.90.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.91.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.91.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.91.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.92.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.92.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.92.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.93.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.93.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.93.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.94.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.94.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.94.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.95.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.95.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.95.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.96.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.96.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.96.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.97.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.97.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.97.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.98.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.98.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.98.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.99.down_proj.weight": "model-00036-of-00049.safetensors", + "model.layers.36.mlp.experts.99.gate_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.experts.99.up_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.mlp.gate.weight": "model-00037-of-00049.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.input_layernorm.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.0.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.0.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.0.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.1.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.1.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.1.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.10.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.10.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.10.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.100.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.100.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.100.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.101.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.101.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.101.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.102.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.102.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.102.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.103.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.103.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.103.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.104.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.104.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.104.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.105.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.105.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.105.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.106.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.106.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.106.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.107.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.107.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.107.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.108.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.108.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.108.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.109.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.109.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.109.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.11.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.11.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.11.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.110.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.110.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.110.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.111.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.111.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.111.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.112.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.112.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.112.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.113.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.113.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.113.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.114.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.114.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.114.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.115.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.115.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.115.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.116.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.116.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.116.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.117.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.117.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.117.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.118.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.118.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.118.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.119.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.119.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.119.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.12.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.12.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.12.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.120.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.120.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.120.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.121.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.121.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.121.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.122.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.122.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.122.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.123.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.123.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.123.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.124.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.124.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.124.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.125.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.125.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.125.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.126.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.126.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.126.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.127.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.127.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.127.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.13.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.13.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.13.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.14.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.14.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.14.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.15.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.15.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.15.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.16.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.16.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.16.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.17.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.17.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.17.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.18.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.18.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.18.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.19.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.19.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.19.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.2.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.2.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.2.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.20.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.20.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.20.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.21.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.21.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.21.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.22.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.22.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.22.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.23.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.23.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.23.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.24.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.24.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.24.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.25.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.25.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.25.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.26.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.26.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.26.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.27.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.27.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.27.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.28.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.28.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.28.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.29.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.29.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.29.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.3.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.3.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.3.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.30.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.30.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.30.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.31.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.31.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.31.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.32.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.32.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.32.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.33.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.33.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.33.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.34.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.34.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.34.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.35.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.35.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.35.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.36.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.36.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.36.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.37.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.37.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.37.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.38.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.38.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.38.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.39.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.39.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.39.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.4.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.4.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.4.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.40.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.40.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.40.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.41.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.41.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.41.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.42.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.42.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.42.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.43.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.43.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.43.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.44.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.44.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.44.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.45.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.45.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.45.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.46.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.46.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.46.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.47.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.47.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.47.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.48.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.48.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.48.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.49.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.49.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.49.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.5.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.5.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.5.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.50.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.50.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.50.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.51.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.51.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.51.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.52.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.52.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.52.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.53.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.53.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.53.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.54.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.54.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.54.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.55.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.55.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.55.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.56.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.56.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.56.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.57.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.57.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.57.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.58.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.58.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.58.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.59.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.59.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.59.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.6.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.6.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.6.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.60.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.60.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.60.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.61.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.61.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.61.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.62.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.62.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.62.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.63.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.63.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.63.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.64.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.64.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.64.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.65.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.65.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.65.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.66.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.66.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.66.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.67.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.67.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.67.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.68.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.68.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.68.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.69.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.69.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.69.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.7.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.7.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.7.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.70.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.70.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.70.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.71.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.71.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.71.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.72.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.72.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.72.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.73.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.73.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.73.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.74.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.74.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.74.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.75.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.75.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.75.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.76.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.76.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.76.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.77.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.77.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.77.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.78.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.78.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.78.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.79.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.79.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.79.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.8.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.8.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.8.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.80.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.80.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.80.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.81.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.81.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.81.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.82.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.82.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.82.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.83.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.83.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.83.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.84.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.84.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.84.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.85.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.85.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.85.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.86.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.86.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.86.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.87.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.87.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.87.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.88.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.88.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.88.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.89.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.89.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.89.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.9.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.9.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.9.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.90.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.90.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.90.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.91.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.91.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.91.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.92.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.92.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.92.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.93.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.93.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.93.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.94.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.94.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.94.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.95.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.95.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.95.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.96.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.96.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.96.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.97.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.97.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.97.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.98.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.98.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.98.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.99.down_proj.weight": "model-00037-of-00049.safetensors", + "model.layers.37.mlp.experts.99.gate_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.experts.99.up_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.mlp.gate.weight": "model-00038-of-00049.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.input_layernorm.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.0.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.0.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.0.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.1.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.1.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.1.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.10.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.10.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.10.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.100.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.100.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.100.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.101.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.101.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.101.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.102.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.102.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.102.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.103.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.103.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.103.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.104.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.104.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.104.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.105.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.105.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.105.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.106.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.106.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.106.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.107.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.107.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.107.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.108.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.108.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.108.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.109.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.109.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.109.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.11.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.11.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.11.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.110.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.110.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.110.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.111.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.111.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.111.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.112.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.112.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.112.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.113.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.113.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.113.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.114.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.114.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.114.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.115.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.115.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.115.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.116.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.116.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.116.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.117.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.117.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.117.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.118.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.118.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.118.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.119.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.119.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.119.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.12.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.12.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.12.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.120.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.120.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.120.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.121.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.121.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.121.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.122.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.122.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.122.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.123.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.123.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.123.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.124.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.124.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.124.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.125.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.125.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.125.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.126.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.126.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.126.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.127.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.127.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.127.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.13.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.13.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.13.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.14.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.14.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.14.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.15.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.15.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.15.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.16.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.16.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.16.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.17.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.17.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.17.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.18.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.18.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.18.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.19.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.19.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.19.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.2.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.2.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.2.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.20.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.20.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.20.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.21.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.21.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.21.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.22.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.22.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.22.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.23.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.23.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.23.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.24.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.24.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.24.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.25.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.25.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.25.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.26.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.26.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.26.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.27.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.27.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.27.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.28.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.28.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.28.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.29.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.29.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.29.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.3.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.3.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.3.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.30.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.30.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.30.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.31.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.31.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.31.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.32.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.32.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.32.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.33.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.33.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.33.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.34.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.34.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.34.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.35.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.35.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.35.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.36.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.36.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.36.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.37.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.37.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.37.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.38.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.38.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.38.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.39.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.39.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.39.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.4.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.4.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.4.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.40.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.40.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.40.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.41.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.41.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.41.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.42.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.42.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.42.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.43.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.43.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.43.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.44.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.44.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.44.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.45.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.45.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.45.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.46.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.46.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.46.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.47.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.47.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.47.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.48.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.48.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.48.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.49.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.49.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.49.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.5.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.5.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.5.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.50.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.50.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.50.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.51.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.51.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.51.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.52.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.52.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.52.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.53.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.53.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.53.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.54.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.54.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.54.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.55.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.55.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.55.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.56.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.56.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.56.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.57.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.57.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.57.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.58.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.58.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.58.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.59.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.59.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.59.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.6.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.6.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.6.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.60.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.60.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.60.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.61.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.61.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.61.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.62.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.62.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.62.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.63.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.63.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.63.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.64.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.64.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.64.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.65.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.65.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.65.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.66.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.66.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.66.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.67.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.67.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.67.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.68.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.68.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.68.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.69.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.69.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.69.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.7.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.7.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.7.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.70.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.70.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.70.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.71.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.71.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.71.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.72.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.72.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.72.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.73.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.73.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.73.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.74.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.74.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.74.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.75.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.75.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.75.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.76.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.76.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.76.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.77.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.77.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.77.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.78.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.78.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.78.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.79.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.79.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.79.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.8.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.8.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.8.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.80.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.80.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.80.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.81.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.81.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.81.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.82.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.82.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.82.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.83.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.83.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.83.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.84.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.84.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.84.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.85.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.85.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.85.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.86.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.86.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.86.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.87.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.87.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.87.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.88.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.88.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.88.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.89.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.89.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.89.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.9.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.9.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.9.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.90.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.90.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.90.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.91.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.91.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.91.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.92.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.92.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.92.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.93.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.93.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.93.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.94.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.94.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.94.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.95.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.95.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.95.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.96.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.96.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.96.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.97.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.97.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.97.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.98.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.98.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.98.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.99.down_proj.weight": "model-00038-of-00049.safetensors", + "model.layers.38.mlp.experts.99.gate_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.experts.99.up_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.mlp.gate.weight": "model-00039-of-00049.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.input_layernorm.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.0.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.0.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.0.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.1.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.1.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.1.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.10.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.10.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.10.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.100.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.100.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.100.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.101.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.101.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.101.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.102.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.102.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.102.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.103.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.103.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.103.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.104.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.104.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.104.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.105.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.105.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.105.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.106.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.106.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.106.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.107.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.107.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.107.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.108.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.108.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.108.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.109.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.109.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.109.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.11.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.11.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.11.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.110.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.110.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.110.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.111.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.111.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.111.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.112.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.112.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.112.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.113.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.113.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.113.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.114.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.114.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.114.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.115.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.115.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.115.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.116.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.116.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.116.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.117.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.117.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.117.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.118.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.118.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.118.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.119.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.119.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.119.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.12.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.12.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.12.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.120.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.120.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.120.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.121.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.121.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.121.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.122.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.122.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.122.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.123.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.123.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.123.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.124.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.124.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.124.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.125.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.125.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.125.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.126.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.126.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.126.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.127.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.127.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.127.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.13.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.13.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.13.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.14.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.14.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.14.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.15.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.15.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.15.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.16.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.16.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.16.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.17.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.17.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.17.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.18.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.18.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.18.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.19.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.19.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.19.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.2.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.2.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.2.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.20.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.20.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.20.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.21.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.21.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.21.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.22.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.22.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.22.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.23.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.23.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.23.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.24.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.24.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.24.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.25.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.25.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.25.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.26.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.26.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.26.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.27.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.27.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.27.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.28.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.28.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.28.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.29.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.29.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.29.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.3.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.3.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.3.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.30.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.30.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.30.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.31.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.31.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.31.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.32.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.32.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.32.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.33.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.33.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.33.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.34.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.34.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.34.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.35.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.35.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.35.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.36.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.36.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.36.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.37.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.37.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.37.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.38.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.38.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.38.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.39.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.39.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.39.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.4.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.4.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.4.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.40.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.40.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.40.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.41.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.41.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.41.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.42.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.42.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.42.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.43.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.43.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.43.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.44.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.44.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.44.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.45.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.45.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.45.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.46.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.46.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.46.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.47.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.47.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.47.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.48.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.48.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.48.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.49.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.49.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.49.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.5.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.5.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.5.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.50.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.50.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.50.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.51.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.51.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.51.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.52.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.52.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.52.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.53.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.53.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.53.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.54.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.54.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.54.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.55.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.55.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.55.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.56.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.56.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.56.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.57.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.57.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.57.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.58.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.58.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.58.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.59.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.59.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.59.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.6.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.6.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.6.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.60.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.60.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.60.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.61.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.61.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.61.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.62.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.62.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.62.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.63.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.63.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.63.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.64.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.64.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.64.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.65.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.65.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.65.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.66.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.66.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.66.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.67.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.67.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.67.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.68.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.68.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.68.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.69.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.69.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.69.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.7.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.7.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.7.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.70.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.70.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.70.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.71.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.71.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.71.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.72.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.72.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.72.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.73.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.73.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.73.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.74.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.74.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.74.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.75.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.75.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.75.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.76.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.76.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.76.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.77.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.77.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.77.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.78.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.78.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.78.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.79.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.79.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.79.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.8.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.8.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.8.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.80.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.80.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.80.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.81.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.81.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.81.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.82.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.82.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.82.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.83.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.83.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.83.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.84.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.84.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.84.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.85.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.85.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.85.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.86.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.86.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.86.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.87.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.87.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.87.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.88.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.88.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.88.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.89.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.89.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.89.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.9.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.9.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.9.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.90.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.90.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.90.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.91.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.91.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.91.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.92.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.92.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.92.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.93.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.93.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.93.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.94.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.94.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.94.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.95.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.95.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.95.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.96.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.96.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.96.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.97.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.97.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.97.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.98.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.98.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.98.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.99.down_proj.weight": "model-00039-of-00049.safetensors", + "model.layers.39.mlp.experts.99.gate_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.experts.99.up_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.mlp.gate.weight": "model-00040-of-00049.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.4.input_layernorm.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.0.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.0.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.1.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.1.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.10.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.10.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.10.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.100.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.100.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.100.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.101.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.101.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.101.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.102.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.102.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.102.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.103.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.103.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.103.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.104.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.104.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.104.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.105.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.105.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.105.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.106.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.106.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.106.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.107.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.107.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.107.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.108.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.108.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.108.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.109.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.109.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.109.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.11.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.11.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.11.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.110.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.110.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.110.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.111.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.111.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.111.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.112.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.112.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.112.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.113.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.113.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.113.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.114.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.114.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.114.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.115.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.115.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.115.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.116.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.116.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.116.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.117.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.117.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.117.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.118.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.118.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.118.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.119.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.119.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.119.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.12.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.12.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.12.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.120.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.120.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.120.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.121.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.121.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.121.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.122.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.122.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.122.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.123.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.123.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.123.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.124.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.124.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.124.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.125.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.125.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.125.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.126.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.126.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.126.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.127.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.127.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.127.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.13.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.13.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.13.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.14.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.14.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.14.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.15.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.15.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.15.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.16.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.16.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.16.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.17.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.17.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.17.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.18.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.18.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.18.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.19.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.19.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.19.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.2.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.2.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.2.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.20.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.20.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.20.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.21.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.21.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.21.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.22.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.22.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.22.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.23.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.23.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.23.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.24.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.24.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.24.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.25.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.25.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.25.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.26.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.26.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.26.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.27.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.27.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.27.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.28.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.28.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.28.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.29.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.29.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.29.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.3.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.3.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.3.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.30.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.30.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.30.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.31.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.31.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.31.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.32.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.32.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.32.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.33.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.33.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.33.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.34.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.34.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.34.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.35.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.35.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.35.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.36.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.36.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.36.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.37.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.37.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.37.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.38.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.38.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.38.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.39.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.39.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.39.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.4.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.4.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.4.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.40.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.40.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.40.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.41.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.41.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.41.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.42.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.42.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.42.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.43.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.43.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.43.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.44.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.44.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.44.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.45.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.45.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.45.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.46.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.46.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.46.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.47.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.47.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.47.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.48.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.48.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.48.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.49.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.49.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.49.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.5.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.5.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.5.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.50.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.50.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.50.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.51.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.51.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.51.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.52.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.52.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.52.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.53.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.53.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.53.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.54.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.54.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.54.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.55.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.55.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.55.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.56.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.56.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.56.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.57.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.57.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.57.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.58.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.58.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.58.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.59.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.59.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.59.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.6.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.6.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.6.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.60.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.60.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.60.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.61.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.61.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.61.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.62.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.62.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.62.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.63.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.63.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.63.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.64.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.64.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.64.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.65.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.65.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.65.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.66.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.66.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.66.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.67.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.67.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.67.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.68.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.68.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.68.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.69.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.69.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.69.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.7.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.7.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.7.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.70.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.70.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.70.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.71.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.71.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.71.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.72.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.72.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.72.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.73.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.73.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.73.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.74.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.74.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.74.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.75.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.75.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.75.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.76.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.76.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.76.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.77.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.77.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.77.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.78.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.78.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.78.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.79.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.79.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.79.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.8.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.8.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.8.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.80.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.80.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.80.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.81.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.81.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.81.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.82.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.82.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.82.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.83.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.83.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.83.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.84.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.84.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.84.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.85.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.85.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.85.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.86.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.86.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.86.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.87.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.87.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.87.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.88.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.88.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.88.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.89.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.89.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.89.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.9.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.9.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.9.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.90.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.90.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.90.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.91.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.91.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.91.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.92.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.92.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.92.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.93.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.93.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.93.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.94.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.94.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.94.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.95.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.95.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.95.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.96.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.96.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.96.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.97.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.97.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.97.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.98.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.98.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.98.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.99.down_proj.weight": "model-00004-of-00049.safetensors", + "model.layers.4.mlp.experts.99.gate_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.experts.99.up_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.mlp.gate.weight": "model-00005-of-00049.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.40.input_layernorm.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.0.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.0.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.0.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.1.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.1.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.1.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.10.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.10.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.10.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.100.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.100.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.100.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.101.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.101.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.101.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.102.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.102.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.102.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.103.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.103.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.103.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.104.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.104.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.104.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.105.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.105.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.105.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.106.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.106.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.106.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.107.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.107.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.107.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.108.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.108.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.108.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.109.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.109.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.109.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.11.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.11.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.11.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.110.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.110.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.110.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.111.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.111.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.111.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.112.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.112.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.112.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.113.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.113.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.113.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.114.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.114.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.114.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.115.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.115.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.115.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.116.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.116.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.116.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.117.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.117.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.117.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.118.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.118.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.118.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.119.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.119.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.119.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.12.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.12.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.12.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.120.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.120.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.120.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.121.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.121.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.121.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.122.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.122.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.122.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.123.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.123.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.123.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.124.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.124.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.124.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.125.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.125.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.125.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.126.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.126.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.126.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.127.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.127.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.127.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.13.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.13.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.13.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.14.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.14.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.14.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.15.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.15.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.15.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.16.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.16.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.16.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.17.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.17.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.17.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.18.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.18.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.18.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.19.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.19.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.19.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.2.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.2.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.2.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.20.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.20.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.20.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.21.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.21.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.21.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.22.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.22.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.22.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.23.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.23.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.23.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.24.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.24.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.24.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.25.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.25.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.25.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.26.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.26.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.26.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.27.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.27.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.27.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.28.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.28.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.28.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.29.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.29.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.29.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.3.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.3.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.3.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.30.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.30.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.30.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.31.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.31.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.31.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.32.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.32.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.32.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.33.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.33.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.33.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.34.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.34.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.34.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.35.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.35.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.35.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.36.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.36.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.36.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.37.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.37.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.37.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.38.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.38.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.38.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.39.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.39.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.39.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.4.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.4.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.4.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.40.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.40.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.40.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.41.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.41.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.41.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.42.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.42.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.42.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.43.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.43.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.43.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.44.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.44.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.44.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.45.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.45.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.45.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.46.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.46.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.46.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.47.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.47.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.47.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.48.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.48.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.48.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.49.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.49.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.49.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.5.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.5.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.5.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.50.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.50.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.50.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.51.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.51.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.51.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.52.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.52.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.52.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.53.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.53.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.53.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.54.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.54.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.54.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.55.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.55.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.55.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.56.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.56.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.56.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.57.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.57.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.57.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.58.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.58.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.58.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.59.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.59.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.59.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.6.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.6.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.6.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.60.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.60.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.60.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.61.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.61.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.61.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.62.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.62.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.62.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.63.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.63.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.63.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.64.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.64.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.64.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.65.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.65.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.65.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.66.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.66.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.66.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.67.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.67.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.67.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.68.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.68.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.68.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.69.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.69.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.69.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.7.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.7.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.7.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.70.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.70.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.70.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.71.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.71.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.71.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.72.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.72.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.72.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.73.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.73.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.73.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.74.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.74.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.74.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.75.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.75.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.75.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.76.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.76.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.76.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.77.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.77.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.77.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.78.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.78.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.78.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.79.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.79.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.79.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.8.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.8.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.8.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.80.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.80.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.80.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.81.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.81.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.81.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.82.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.82.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.82.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.83.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.83.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.83.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.84.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.84.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.84.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.85.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.85.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.85.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.86.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.86.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.86.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.87.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.87.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.87.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.88.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.88.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.88.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.89.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.89.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.89.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.9.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.9.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.9.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.90.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.90.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.90.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.91.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.91.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.91.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.92.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.92.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.92.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.93.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.93.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.93.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.94.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.94.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.94.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.95.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.95.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.95.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.96.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.96.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.96.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.97.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.97.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.97.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.98.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.98.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.98.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.99.down_proj.weight": "model-00040-of-00049.safetensors", + "model.layers.40.mlp.experts.99.gate_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.experts.99.up_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.mlp.gate.weight": "model-00041-of-00049.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.input_layernorm.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.0.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.0.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.0.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.1.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.1.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.1.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.10.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.10.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.10.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.100.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.100.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.100.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.101.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.101.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.101.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.102.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.102.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.102.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.103.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.103.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.103.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.104.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.104.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.104.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.105.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.105.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.105.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.106.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.106.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.106.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.107.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.107.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.107.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.108.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.108.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.108.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.109.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.109.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.109.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.11.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.11.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.11.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.110.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.110.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.110.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.111.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.111.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.111.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.112.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.112.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.112.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.113.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.113.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.113.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.114.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.114.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.114.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.115.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.115.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.115.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.116.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.116.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.116.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.117.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.117.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.117.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.118.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.118.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.118.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.119.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.119.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.119.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.12.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.12.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.12.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.120.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.120.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.120.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.121.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.121.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.121.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.122.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.122.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.122.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.123.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.123.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.123.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.124.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.124.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.124.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.125.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.125.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.125.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.126.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.126.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.126.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.127.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.127.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.127.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.13.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.13.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.13.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.14.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.14.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.14.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.15.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.15.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.15.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.16.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.16.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.16.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.17.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.17.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.17.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.18.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.18.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.18.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.19.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.19.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.19.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.2.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.2.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.2.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.20.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.20.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.20.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.21.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.21.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.21.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.22.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.22.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.22.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.23.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.23.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.23.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.24.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.24.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.24.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.25.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.25.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.25.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.26.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.26.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.26.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.27.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.27.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.27.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.28.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.28.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.28.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.29.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.29.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.29.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.3.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.3.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.3.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.30.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.30.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.30.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.31.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.31.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.31.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.32.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.32.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.32.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.33.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.33.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.33.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.34.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.34.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.34.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.35.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.35.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.35.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.36.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.36.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.36.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.37.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.37.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.37.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.38.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.38.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.38.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.39.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.39.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.39.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.4.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.4.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.4.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.40.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.40.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.40.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.41.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.41.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.41.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.42.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.42.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.42.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.43.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.43.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.43.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.44.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.44.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.44.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.45.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.45.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.45.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.46.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.46.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.46.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.47.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.47.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.47.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.48.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.48.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.48.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.49.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.49.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.49.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.5.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.5.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.5.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.50.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.50.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.50.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.51.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.51.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.51.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.52.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.52.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.52.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.53.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.53.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.53.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.54.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.54.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.54.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.55.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.55.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.55.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.56.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.56.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.56.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.57.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.57.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.57.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.58.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.58.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.58.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.59.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.59.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.59.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.6.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.6.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.6.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.60.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.60.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.60.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.61.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.61.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.61.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.62.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.62.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.62.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.63.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.63.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.63.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.64.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.64.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.64.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.65.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.65.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.65.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.66.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.66.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.66.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.67.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.67.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.67.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.68.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.68.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.68.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.69.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.69.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.69.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.7.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.7.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.7.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.70.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.70.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.70.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.71.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.71.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.71.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.72.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.72.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.72.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.73.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.73.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.73.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.74.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.74.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.74.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.75.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.75.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.75.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.76.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.76.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.76.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.77.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.77.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.77.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.78.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.78.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.78.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.79.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.79.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.79.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.8.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.8.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.8.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.80.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.80.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.80.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.81.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.81.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.81.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.82.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.82.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.82.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.83.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.83.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.83.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.84.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.84.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.84.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.85.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.85.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.85.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.86.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.86.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.86.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.87.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.87.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.87.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.88.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.88.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.88.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.89.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.89.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.89.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.9.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.9.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.9.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.90.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.90.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.90.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.91.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.91.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.91.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.92.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.92.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.92.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.93.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.93.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.93.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.94.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.94.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.94.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.95.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.95.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.95.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.96.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.96.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.96.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.97.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.97.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.97.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.98.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.98.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.98.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.99.down_proj.weight": "model-00041-of-00049.safetensors", + "model.layers.41.mlp.experts.99.gate_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.experts.99.up_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.mlp.gate.weight": "model-00042-of-00049.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.input_layernorm.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.0.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.0.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.0.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.1.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.1.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.1.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.10.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.10.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.10.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.100.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.100.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.100.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.101.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.101.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.101.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.102.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.102.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.102.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.103.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.103.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.103.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.104.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.104.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.104.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.105.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.105.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.105.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.106.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.106.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.106.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.107.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.107.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.107.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.108.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.108.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.108.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.109.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.109.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.109.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.11.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.11.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.11.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.110.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.110.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.110.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.111.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.111.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.111.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.112.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.112.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.112.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.113.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.113.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.113.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.114.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.114.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.114.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.115.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.115.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.115.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.116.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.116.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.116.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.117.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.117.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.117.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.118.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.118.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.118.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.119.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.119.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.119.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.12.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.12.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.12.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.120.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.120.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.120.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.121.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.121.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.121.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.122.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.122.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.122.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.123.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.123.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.123.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.124.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.124.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.124.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.125.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.125.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.125.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.126.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.126.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.126.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.127.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.127.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.127.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.13.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.13.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.13.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.14.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.14.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.14.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.15.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.15.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.15.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.16.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.16.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.16.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.17.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.17.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.17.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.18.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.18.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.18.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.19.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.19.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.19.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.2.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.2.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.2.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.20.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.20.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.20.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.21.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.21.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.21.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.22.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.22.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.22.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.23.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.23.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.23.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.24.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.24.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.24.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.25.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.25.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.25.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.26.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.26.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.26.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.27.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.27.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.27.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.28.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.28.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.28.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.29.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.29.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.29.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.3.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.3.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.3.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.30.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.30.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.30.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.31.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.31.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.31.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.32.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.32.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.32.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.33.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.33.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.33.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.34.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.34.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.34.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.35.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.35.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.35.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.36.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.36.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.36.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.37.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.37.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.37.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.38.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.38.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.38.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.39.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.39.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.39.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.4.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.4.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.4.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.40.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.40.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.40.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.41.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.41.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.41.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.42.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.42.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.42.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.43.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.43.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.43.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.44.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.44.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.44.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.45.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.45.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.45.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.46.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.46.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.46.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.47.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.47.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.47.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.48.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.48.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.48.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.49.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.49.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.49.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.5.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.5.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.5.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.50.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.50.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.50.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.51.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.51.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.51.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.52.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.52.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.52.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.53.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.53.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.53.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.54.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.54.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.54.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.55.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.55.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.55.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.56.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.56.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.56.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.57.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.57.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.57.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.58.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.58.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.58.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.59.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.59.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.59.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.6.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.6.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.6.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.60.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.60.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.60.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.61.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.61.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.61.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.62.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.62.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.62.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.63.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.63.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.63.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.64.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.64.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.64.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.65.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.65.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.65.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.66.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.66.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.66.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.67.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.67.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.67.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.68.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.68.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.68.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.69.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.69.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.69.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.7.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.7.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.7.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.70.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.70.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.70.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.71.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.71.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.71.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.72.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.72.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.72.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.73.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.73.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.73.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.74.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.74.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.74.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.75.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.75.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.75.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.76.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.76.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.76.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.77.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.77.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.77.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.78.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.78.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.78.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.79.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.79.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.79.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.8.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.8.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.8.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.80.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.80.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.80.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.81.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.81.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.81.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.82.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.82.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.82.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.83.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.83.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.83.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.84.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.84.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.84.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.85.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.85.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.85.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.86.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.86.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.86.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.87.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.87.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.87.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.88.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.88.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.88.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.89.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.89.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.89.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.9.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.9.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.9.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.90.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.90.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.90.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.91.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.91.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.91.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.92.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.92.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.92.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.93.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.93.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.93.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.94.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.94.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.94.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.95.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.95.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.95.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.96.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.96.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.96.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.97.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.97.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.97.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.98.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.98.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.98.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.99.down_proj.weight": "model-00042-of-00049.safetensors", + "model.layers.42.mlp.experts.99.gate_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.experts.99.up_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.mlp.gate.weight": "model-00043-of-00049.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.input_layernorm.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.0.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.0.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.0.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.1.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.1.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.1.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.10.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.10.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.10.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.100.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.100.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.100.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.101.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.101.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.101.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.102.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.102.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.102.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.103.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.103.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.103.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.104.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.104.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.104.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.105.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.105.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.105.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.106.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.106.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.106.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.107.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.107.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.107.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.108.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.108.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.108.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.109.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.109.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.109.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.11.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.11.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.11.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.110.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.110.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.110.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.111.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.111.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.111.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.112.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.112.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.112.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.113.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.113.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.113.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.114.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.114.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.114.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.115.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.115.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.115.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.116.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.116.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.116.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.117.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.117.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.117.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.118.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.118.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.118.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.119.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.119.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.119.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.12.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.12.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.12.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.120.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.120.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.120.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.121.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.121.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.121.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.122.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.122.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.122.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.123.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.123.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.123.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.124.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.124.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.124.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.125.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.125.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.125.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.126.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.126.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.126.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.127.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.127.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.127.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.13.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.13.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.13.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.14.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.14.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.14.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.15.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.15.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.15.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.16.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.16.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.16.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.17.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.17.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.17.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.18.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.18.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.18.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.19.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.19.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.19.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.2.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.2.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.2.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.20.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.20.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.20.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.21.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.21.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.21.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.22.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.22.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.22.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.23.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.23.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.23.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.24.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.24.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.24.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.25.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.25.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.25.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.26.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.26.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.26.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.27.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.27.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.27.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.28.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.28.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.28.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.29.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.29.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.29.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.3.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.3.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.3.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.30.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.30.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.30.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.31.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.31.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.31.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.32.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.32.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.32.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.33.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.33.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.33.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.34.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.34.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.34.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.35.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.35.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.35.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.36.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.36.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.36.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.37.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.37.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.37.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.38.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.38.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.38.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.39.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.39.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.39.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.4.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.4.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.4.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.40.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.40.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.40.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.41.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.41.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.41.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.42.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.42.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.42.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.43.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.43.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.43.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.44.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.44.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.44.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.45.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.45.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.45.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.46.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.46.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.46.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.47.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.47.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.47.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.48.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.48.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.48.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.49.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.49.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.49.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.5.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.5.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.5.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.50.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.50.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.50.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.51.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.51.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.51.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.52.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.52.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.52.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.53.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.53.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.53.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.54.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.54.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.54.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.55.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.55.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.55.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.56.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.56.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.56.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.57.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.57.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.57.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.58.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.58.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.58.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.59.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.59.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.59.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.6.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.6.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.6.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.60.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.60.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.60.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.61.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.61.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.61.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.62.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.62.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.62.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.63.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.63.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.63.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.64.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.64.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.64.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.65.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.65.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.65.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.66.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.66.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.66.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.67.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.67.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.67.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.68.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.68.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.68.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.69.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.69.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.69.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.7.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.7.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.7.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.70.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.70.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.70.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.71.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.71.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.71.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.72.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.72.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.72.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.73.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.73.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.73.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.74.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.74.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.74.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.75.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.75.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.75.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.76.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.76.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.76.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.77.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.77.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.77.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.78.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.78.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.78.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.79.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.79.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.79.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.8.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.8.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.8.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.80.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.80.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.80.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.81.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.81.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.81.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.82.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.82.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.82.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.83.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.83.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.83.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.84.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.84.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.84.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.85.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.85.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.85.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.86.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.86.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.86.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.87.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.87.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.87.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.88.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.88.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.88.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.89.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.89.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.89.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.9.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.9.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.9.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.90.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.90.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.90.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.91.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.91.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.91.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.92.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.92.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.92.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.93.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.93.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.93.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.94.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.94.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.94.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.95.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.95.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.95.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.96.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.96.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.96.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.97.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.97.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.97.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.98.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.98.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.98.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.99.down_proj.weight": "model-00043-of-00049.safetensors", + "model.layers.43.mlp.experts.99.gate_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.experts.99.up_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.mlp.gate.weight": "model-00044-of-00049.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.input_layernorm.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.0.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.0.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.0.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.1.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.1.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.1.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.10.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.10.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.10.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.100.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.100.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.100.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.101.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.101.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.101.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.102.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.102.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.102.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.103.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.103.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.103.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.104.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.104.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.104.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.105.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.105.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.105.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.106.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.106.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.106.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.107.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.107.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.107.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.108.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.108.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.108.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.109.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.109.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.109.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.11.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.11.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.11.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.110.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.110.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.110.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.111.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.111.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.111.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.112.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.112.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.112.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.113.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.113.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.113.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.114.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.114.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.114.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.115.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.115.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.115.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.116.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.116.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.116.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.117.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.117.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.117.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.118.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.118.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.118.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.119.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.119.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.119.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.12.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.12.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.12.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.120.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.120.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.120.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.121.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.121.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.121.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.122.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.122.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.122.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.123.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.123.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.123.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.124.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.124.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.124.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.125.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.125.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.125.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.126.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.126.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.126.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.127.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.127.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.127.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.13.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.13.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.13.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.14.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.14.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.14.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.15.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.15.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.15.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.16.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.16.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.16.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.17.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.17.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.17.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.18.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.18.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.18.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.19.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.19.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.19.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.2.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.2.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.2.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.20.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.20.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.20.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.21.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.21.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.21.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.22.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.22.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.22.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.23.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.23.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.23.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.24.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.24.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.24.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.25.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.25.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.25.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.26.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.26.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.26.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.27.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.27.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.27.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.28.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.28.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.28.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.29.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.29.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.29.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.3.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.3.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.3.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.30.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.30.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.30.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.31.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.31.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.31.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.32.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.32.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.32.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.33.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.33.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.33.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.34.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.34.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.34.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.35.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.35.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.35.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.36.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.36.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.36.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.37.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.37.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.37.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.38.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.38.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.38.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.39.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.39.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.39.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.4.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.4.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.4.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.40.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.40.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.40.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.41.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.41.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.41.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.42.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.42.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.42.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.43.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.43.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.43.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.44.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.44.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.44.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.45.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.45.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.45.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.46.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.46.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.46.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.47.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.47.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.47.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.48.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.48.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.48.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.49.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.49.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.49.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.5.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.5.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.5.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.50.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.50.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.50.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.51.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.51.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.51.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.52.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.52.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.52.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.53.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.53.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.53.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.54.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.54.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.54.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.55.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.55.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.55.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.56.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.56.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.56.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.57.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.57.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.57.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.58.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.58.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.58.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.59.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.59.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.59.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.6.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.6.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.6.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.60.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.60.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.60.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.61.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.61.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.61.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.62.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.62.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.62.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.63.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.63.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.63.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.64.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.64.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.64.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.65.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.65.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.65.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.66.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.66.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.66.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.67.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.67.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.67.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.68.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.68.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.68.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.69.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.69.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.69.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.7.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.7.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.7.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.70.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.70.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.70.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.71.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.71.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.71.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.72.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.72.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.72.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.73.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.73.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.73.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.74.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.74.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.74.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.75.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.75.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.75.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.76.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.76.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.76.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.77.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.77.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.77.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.78.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.78.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.78.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.79.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.79.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.79.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.8.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.8.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.8.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.80.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.80.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.80.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.81.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.81.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.81.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.82.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.82.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.82.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.83.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.83.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.83.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.84.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.84.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.84.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.85.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.85.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.85.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.86.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.86.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.86.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.87.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.87.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.87.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.88.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.88.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.88.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.89.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.89.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.89.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.9.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.9.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.9.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.90.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.90.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.90.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.91.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.91.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.91.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.92.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.92.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.92.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.93.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.93.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.93.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.94.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.94.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.94.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.95.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.95.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.95.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.96.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.96.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.96.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.97.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.97.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.97.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.98.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.98.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.98.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.99.down_proj.weight": "model-00044-of-00049.safetensors", + "model.layers.44.mlp.experts.99.gate_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.experts.99.up_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.mlp.gate.weight": "model-00045-of-00049.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.input_layernorm.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.0.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.0.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.0.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.1.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.1.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.1.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.10.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.10.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.10.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.100.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.100.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.100.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.101.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.101.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.101.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.102.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.102.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.102.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.103.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.103.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.103.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.104.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.104.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.104.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.105.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.105.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.105.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.106.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.106.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.106.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.107.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.107.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.107.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.108.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.108.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.108.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.109.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.109.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.109.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.11.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.11.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.11.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.110.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.110.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.110.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.111.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.111.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.111.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.112.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.112.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.112.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.113.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.113.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.113.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.114.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.114.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.114.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.115.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.115.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.115.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.116.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.116.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.116.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.117.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.117.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.117.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.118.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.118.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.118.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.119.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.119.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.119.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.12.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.12.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.12.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.120.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.120.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.120.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.121.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.121.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.121.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.122.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.122.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.122.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.123.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.123.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.123.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.124.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.124.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.124.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.125.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.125.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.125.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.126.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.126.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.126.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.127.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.127.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.127.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.13.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.13.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.13.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.14.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.14.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.14.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.15.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.15.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.15.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.16.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.16.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.16.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.17.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.17.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.17.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.18.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.18.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.18.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.19.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.19.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.19.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.2.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.2.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.2.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.20.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.20.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.20.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.21.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.21.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.21.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.22.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.22.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.22.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.23.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.23.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.23.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.24.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.24.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.24.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.25.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.25.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.25.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.26.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.26.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.26.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.27.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.27.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.27.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.28.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.28.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.28.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.29.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.29.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.29.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.3.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.3.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.3.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.30.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.30.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.30.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.31.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.31.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.31.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.32.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.32.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.32.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.33.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.33.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.33.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.34.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.34.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.34.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.35.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.35.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.35.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.36.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.36.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.36.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.37.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.37.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.37.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.38.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.38.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.38.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.39.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.39.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.39.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.4.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.4.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.4.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.40.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.40.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.40.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.41.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.41.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.41.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.42.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.42.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.42.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.43.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.43.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.43.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.44.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.44.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.44.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.45.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.45.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.45.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.46.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.46.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.46.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.47.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.47.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.47.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.48.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.48.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.48.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.49.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.49.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.49.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.5.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.5.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.5.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.50.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.50.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.50.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.51.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.51.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.51.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.52.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.52.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.52.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.53.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.53.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.53.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.54.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.54.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.54.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.55.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.55.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.55.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.56.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.56.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.56.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.57.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.57.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.57.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.58.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.58.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.58.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.59.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.59.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.59.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.6.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.6.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.6.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.60.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.60.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.60.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.61.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.61.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.61.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.62.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.62.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.62.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.63.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.63.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.63.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.64.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.64.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.64.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.65.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.65.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.65.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.66.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.66.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.66.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.67.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.67.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.67.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.68.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.68.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.68.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.69.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.69.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.69.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.7.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.7.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.7.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.70.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.70.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.70.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.71.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.71.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.71.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.72.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.72.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.72.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.73.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.73.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.73.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.74.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.74.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.74.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.75.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.75.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.75.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.76.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.76.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.76.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.77.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.77.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.77.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.78.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.78.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.78.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.79.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.79.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.79.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.8.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.8.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.8.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.80.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.80.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.80.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.81.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.81.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.81.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.82.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.82.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.82.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.83.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.83.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.83.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.84.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.84.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.84.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.85.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.85.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.85.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.86.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.86.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.86.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.87.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.87.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.87.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.88.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.88.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.88.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.89.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.89.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.89.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.9.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.9.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.9.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.90.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.90.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.90.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.91.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.91.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.91.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.92.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.92.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.92.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.93.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.93.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.93.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.94.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.94.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.94.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.95.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.95.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.95.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.96.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.96.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.96.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.97.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.97.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.97.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.98.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.98.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.98.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.99.down_proj.weight": "model-00045-of-00049.safetensors", + "model.layers.45.mlp.experts.99.gate_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.experts.99.up_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.mlp.gate.weight": "model-00046-of-00049.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.input_layernorm.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.0.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.0.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.0.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.1.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.1.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.1.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.10.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.10.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.10.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.100.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.100.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.100.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.101.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.101.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.101.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.102.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.102.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.102.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.103.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.103.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.103.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.104.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.104.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.104.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.105.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.105.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.105.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.106.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.106.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.106.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.107.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.107.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.107.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.108.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.108.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.108.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.109.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.109.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.109.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.11.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.11.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.11.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.110.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.110.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.110.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.111.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.111.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.111.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.112.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.112.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.112.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.113.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.113.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.113.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.114.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.114.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.114.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.115.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.115.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.115.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.116.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.116.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.116.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.117.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.117.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.117.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.118.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.118.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.118.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.119.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.119.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.119.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.12.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.12.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.12.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.120.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.120.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.120.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.121.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.121.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.121.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.122.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.122.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.122.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.123.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.123.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.123.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.124.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.124.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.124.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.125.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.125.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.125.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.126.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.126.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.126.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.127.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.127.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.127.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.13.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.13.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.13.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.14.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.14.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.14.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.15.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.15.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.15.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.16.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.16.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.16.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.17.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.17.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.17.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.18.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.18.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.18.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.19.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.19.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.19.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.2.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.2.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.2.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.20.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.20.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.20.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.21.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.21.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.21.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.22.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.22.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.22.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.23.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.23.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.23.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.24.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.24.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.24.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.25.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.25.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.25.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.26.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.26.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.26.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.27.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.27.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.27.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.28.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.28.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.28.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.29.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.29.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.29.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.3.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.3.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.3.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.30.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.30.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.30.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.31.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.31.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.31.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.32.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.32.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.32.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.33.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.33.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.33.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.34.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.34.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.34.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.35.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.35.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.35.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.36.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.36.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.36.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.37.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.37.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.37.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.38.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.38.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.38.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.39.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.39.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.39.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.4.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.4.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.4.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.40.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.40.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.40.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.41.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.41.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.41.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.42.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.42.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.42.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.43.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.43.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.43.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.44.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.44.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.44.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.45.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.45.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.45.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.46.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.46.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.46.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.47.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.47.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.47.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.48.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.48.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.48.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.49.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.49.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.49.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.5.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.5.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.5.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.50.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.50.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.50.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.51.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.51.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.51.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.52.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.52.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.52.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.53.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.53.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.53.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.54.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.54.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.54.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.55.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.55.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.55.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.56.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.56.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.56.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.57.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.57.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.57.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.58.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.58.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.58.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.59.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.59.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.59.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.6.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.6.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.6.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.60.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.60.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.60.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.61.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.61.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.61.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.62.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.62.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.62.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.63.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.63.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.63.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.64.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.64.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.64.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.65.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.65.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.65.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.66.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.66.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.66.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.67.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.67.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.67.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.68.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.68.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.68.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.69.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.69.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.69.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.7.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.7.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.7.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.70.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.70.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.70.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.71.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.71.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.71.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.72.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.72.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.72.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.73.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.73.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.73.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.74.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.74.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.74.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.75.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.75.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.75.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.76.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.76.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.76.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.77.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.77.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.77.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.78.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.78.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.78.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.79.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.79.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.79.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.8.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.8.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.8.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.80.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.80.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.80.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.81.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.81.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.81.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.82.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.82.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.82.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.83.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.83.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.83.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.84.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.84.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.84.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.85.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.85.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.85.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.86.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.86.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.86.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.87.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.87.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.87.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.88.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.88.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.88.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.89.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.89.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.89.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.9.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.9.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.9.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.90.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.90.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.90.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.91.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.91.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.91.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.92.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.92.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.92.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.93.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.93.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.93.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.94.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.94.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.94.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.95.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.95.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.95.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.96.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.96.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.96.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.97.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.97.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.97.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.98.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.98.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.98.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.99.down_proj.weight": "model-00046-of-00049.safetensors", + "model.layers.46.mlp.experts.99.gate_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.experts.99.up_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.mlp.gate.weight": "model-00047-of-00049.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.input_layernorm.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.0.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.0.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.0.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.1.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.1.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.1.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.10.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.10.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.10.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.100.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.100.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.100.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.101.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.101.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.101.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.102.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.102.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.102.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.103.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.103.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.103.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.104.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.104.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.104.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.105.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.105.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.105.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.106.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.106.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.106.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.107.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.107.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.107.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.108.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.108.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.108.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.109.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.109.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.109.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.11.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.11.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.11.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.110.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.110.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.110.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.111.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.111.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.111.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.112.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.112.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.112.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.113.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.113.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.113.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.114.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.114.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.114.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.115.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.115.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.115.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.116.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.116.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.116.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.117.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.117.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.117.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.118.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.118.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.118.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.119.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.119.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.119.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.12.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.12.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.12.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.120.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.120.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.120.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.121.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.121.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.121.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.122.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.122.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.122.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.123.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.123.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.123.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.124.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.124.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.124.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.125.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.125.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.125.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.126.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.126.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.126.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.127.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.127.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.127.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.13.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.13.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.13.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.14.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.14.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.14.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.15.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.15.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.15.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.16.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.16.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.16.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.17.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.17.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.17.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.18.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.18.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.18.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.19.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.19.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.19.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.2.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.2.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.2.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.20.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.20.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.20.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.21.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.21.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.21.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.22.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.22.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.22.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.23.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.23.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.23.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.24.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.24.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.24.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.25.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.25.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.25.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.26.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.26.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.26.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.27.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.27.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.27.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.28.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.28.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.28.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.29.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.29.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.29.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.3.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.3.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.3.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.30.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.30.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.30.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.31.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.31.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.31.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.32.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.32.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.32.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.33.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.33.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.33.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.34.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.34.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.34.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.35.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.35.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.35.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.36.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.36.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.36.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.37.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.37.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.37.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.38.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.38.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.38.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.39.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.39.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.39.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.4.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.4.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.4.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.40.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.40.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.40.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.41.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.41.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.41.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.42.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.42.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.42.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.43.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.43.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.43.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.44.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.44.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.44.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.45.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.45.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.45.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.46.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.46.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.46.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.47.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.47.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.47.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.48.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.48.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.48.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.49.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.49.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.49.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.5.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.5.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.5.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.50.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.50.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.50.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.51.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.51.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.51.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.52.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.52.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.52.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.53.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.53.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.53.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.54.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.54.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.54.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.55.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.55.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.55.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.56.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.56.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.56.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.57.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.57.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.57.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.58.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.58.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.58.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.59.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.59.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.59.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.6.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.6.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.6.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.60.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.60.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.60.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.61.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.61.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.61.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.62.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.62.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.62.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.63.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.63.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.63.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.64.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.64.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.64.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.65.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.65.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.65.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.66.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.66.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.66.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.67.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.67.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.67.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.68.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.68.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.68.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.69.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.69.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.69.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.7.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.7.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.7.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.70.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.70.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.70.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.71.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.71.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.71.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.72.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.72.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.72.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.73.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.73.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.73.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.74.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.74.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.74.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.75.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.75.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.75.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.76.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.76.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.76.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.77.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.77.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.77.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.78.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.78.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.78.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.79.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.79.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.79.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.8.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.8.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.8.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.80.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.80.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.80.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.81.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.81.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.81.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.82.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.82.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.82.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.83.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.83.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.83.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.84.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.84.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.84.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.85.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.85.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.85.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.86.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.86.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.86.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.87.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.87.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.87.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.88.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.88.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.88.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.89.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.89.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.89.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.9.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.9.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.9.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.90.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.90.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.90.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.91.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.91.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.91.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.92.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.92.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.92.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.93.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.93.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.93.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.94.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.94.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.94.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.95.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.95.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.95.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.96.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.96.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.96.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.97.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.97.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.97.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.98.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.98.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.98.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.99.down_proj.weight": "model-00047-of-00049.safetensors", + "model.layers.47.mlp.experts.99.gate_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.experts.99.up_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.mlp.gate.weight": "model-00048-of-00049.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.input_layernorm.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.0.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.0.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.0.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.1.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.1.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.1.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.10.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.10.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.10.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.100.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.100.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.100.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.101.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.101.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.101.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.102.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.102.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.102.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.103.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.103.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.103.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.104.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.104.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.104.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.105.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.105.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.105.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.106.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.106.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.106.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.107.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.107.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.107.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.108.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.108.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.108.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.109.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.109.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.109.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.11.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.11.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.11.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.110.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.110.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.110.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.111.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.111.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.111.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.112.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.112.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.112.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.113.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.113.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.113.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.114.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.114.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.114.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.115.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.115.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.115.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.116.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.116.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.116.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.117.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.117.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.117.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.118.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.118.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.118.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.119.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.119.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.119.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.12.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.12.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.12.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.120.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.120.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.120.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.121.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.121.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.121.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.122.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.122.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.122.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.123.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.123.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.123.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.124.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.124.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.124.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.125.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.125.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.125.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.126.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.126.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.126.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.127.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.127.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.127.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.13.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.13.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.13.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.14.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.14.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.14.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.15.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.15.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.15.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.16.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.16.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.16.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.17.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.17.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.17.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.18.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.18.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.18.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.19.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.19.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.19.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.2.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.2.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.2.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.20.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.20.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.20.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.21.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.21.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.21.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.22.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.22.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.22.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.23.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.23.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.23.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.24.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.24.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.24.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.25.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.25.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.25.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.26.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.26.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.26.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.27.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.27.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.27.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.28.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.28.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.28.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.29.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.29.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.29.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.3.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.3.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.3.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.30.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.30.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.30.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.31.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.31.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.31.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.32.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.32.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.32.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.33.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.33.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.33.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.34.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.34.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.34.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.35.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.35.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.35.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.36.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.36.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.36.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.37.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.37.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.37.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.38.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.38.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.38.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.39.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.39.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.39.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.4.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.4.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.4.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.40.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.40.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.40.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.41.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.41.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.41.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.42.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.42.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.42.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.43.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.43.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.43.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.44.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.44.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.44.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.45.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.45.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.45.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.46.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.46.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.46.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.47.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.47.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.47.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.48.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.48.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.48.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.49.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.49.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.49.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.5.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.5.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.5.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.50.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.50.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.50.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.51.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.51.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.51.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.52.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.52.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.52.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.53.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.53.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.53.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.54.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.54.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.54.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.55.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.55.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.55.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.56.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.56.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.56.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.57.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.57.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.57.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.58.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.58.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.58.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.59.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.59.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.59.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.6.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.6.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.6.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.60.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.60.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.60.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.61.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.61.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.61.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.62.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.62.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.62.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.63.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.63.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.63.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.64.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.64.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.64.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.65.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.65.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.65.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.66.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.66.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.66.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.67.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.67.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.67.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.68.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.68.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.68.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.69.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.69.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.69.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.7.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.7.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.7.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.70.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.70.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.70.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.71.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.71.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.71.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.72.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.72.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.72.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.73.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.73.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.73.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.74.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.74.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.74.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.75.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.75.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.75.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.76.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.76.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.76.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.77.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.77.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.77.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.78.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.78.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.78.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.79.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.79.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.79.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.8.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.8.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.8.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.80.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.80.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.80.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.81.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.81.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.81.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.82.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.82.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.82.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.83.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.83.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.83.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.84.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.84.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.84.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.85.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.85.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.85.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.86.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.86.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.86.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.87.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.87.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.87.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.88.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.88.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.88.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.89.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.89.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.89.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.9.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.9.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.9.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.90.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.90.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.90.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.91.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.91.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.91.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.92.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.92.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.92.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.93.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.93.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.93.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.94.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.94.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.94.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.95.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.95.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.95.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.96.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.96.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.96.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.97.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.97.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.97.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.98.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.98.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.98.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.99.down_proj.weight": "model-00048-of-00049.safetensors", + "model.layers.48.mlp.experts.99.gate_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.experts.99.up_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.mlp.gate.weight": "model-00049-of-00049.safetensors", + "model.layers.48.self_attn.k_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.self_attn.o_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.self_attn.q_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.48.self_attn.v_proj.weight": "model-00049-of-00049.safetensors", + "model.layers.5.input_layernorm.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.0.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.0.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.0.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.1.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.1.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.1.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.10.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.10.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.10.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.100.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.100.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.100.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.101.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.101.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.101.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.102.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.102.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.102.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.103.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.103.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.103.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.104.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.104.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.104.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.105.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.105.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.105.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.106.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.106.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.106.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.107.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.107.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.107.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.108.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.108.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.108.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.109.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.109.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.109.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.11.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.11.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.11.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.110.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.110.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.110.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.111.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.111.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.111.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.112.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.112.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.112.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.113.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.113.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.113.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.114.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.114.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.114.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.115.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.115.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.115.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.116.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.116.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.116.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.117.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.117.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.117.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.118.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.118.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.118.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.119.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.119.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.119.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.12.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.12.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.12.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.120.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.120.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.120.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.121.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.121.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.121.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.122.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.122.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.122.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.123.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.123.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.123.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.124.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.124.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.124.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.125.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.125.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.125.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.126.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.126.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.126.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.127.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.127.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.127.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.13.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.13.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.13.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.14.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.14.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.14.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.15.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.15.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.15.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.16.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.16.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.16.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.17.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.17.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.17.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.18.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.18.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.18.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.19.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.19.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.19.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.2.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.2.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.2.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.20.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.20.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.20.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.21.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.21.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.21.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.22.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.22.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.22.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.23.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.23.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.23.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.24.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.24.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.24.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.25.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.25.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.25.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.26.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.26.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.26.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.27.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.27.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.27.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.28.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.28.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.28.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.29.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.29.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.29.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.3.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.3.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.3.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.30.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.30.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.30.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.31.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.31.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.31.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.32.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.32.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.32.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.33.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.33.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.33.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.34.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.34.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.34.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.35.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.35.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.35.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.36.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.36.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.36.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.37.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.37.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.37.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.38.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.38.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.38.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.39.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.39.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.39.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.4.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.4.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.4.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.40.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.40.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.40.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.41.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.41.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.41.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.42.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.42.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.42.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.43.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.43.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.43.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.44.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.44.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.44.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.45.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.45.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.45.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.46.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.46.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.46.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.47.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.47.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.47.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.48.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.48.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.48.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.49.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.49.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.49.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.5.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.5.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.5.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.50.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.50.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.50.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.51.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.51.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.51.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.52.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.52.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.52.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.53.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.53.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.53.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.54.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.54.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.54.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.55.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.55.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.55.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.56.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.56.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.56.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.57.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.57.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.57.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.58.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.58.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.58.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.59.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.59.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.59.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.6.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.6.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.6.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.60.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.60.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.60.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.61.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.61.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.61.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.62.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.62.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.62.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.63.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.63.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.63.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.64.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.64.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.64.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.65.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.65.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.65.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.66.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.66.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.66.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.67.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.67.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.67.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.68.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.68.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.68.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.69.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.69.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.69.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.7.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.7.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.7.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.70.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.70.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.70.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.71.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.71.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.71.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.72.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.72.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.72.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.73.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.73.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.73.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.74.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.74.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.74.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.75.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.75.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.75.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.76.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.76.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.76.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.77.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.77.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.77.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.78.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.78.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.78.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.79.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.79.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.79.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.8.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.8.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.8.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.80.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.80.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.80.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.81.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.81.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.81.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.82.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.82.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.82.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.83.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.83.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.83.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.84.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.84.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.84.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.85.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.85.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.85.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.86.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.86.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.86.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.87.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.87.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.87.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.88.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.88.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.88.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.89.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.89.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.89.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.9.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.9.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.9.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.90.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.90.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.90.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.91.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.91.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.91.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.92.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.92.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.92.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.93.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.93.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.93.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.94.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.94.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.94.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.95.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.95.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.95.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.96.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.96.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.96.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.97.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.97.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.97.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.98.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.98.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.98.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.99.down_proj.weight": "model-00005-of-00049.safetensors", + "model.layers.5.mlp.experts.99.gate_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.experts.99.up_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.mlp.gate.weight": "model-00006-of-00049.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.input_layernorm.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.0.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.0.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.0.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.1.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.1.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.1.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.10.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.10.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.10.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.100.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.100.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.100.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.101.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.101.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.101.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.102.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.102.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.102.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.103.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.103.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.103.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.104.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.104.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.104.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.105.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.105.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.105.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.106.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.106.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.106.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.107.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.107.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.107.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.108.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.108.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.108.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.109.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.109.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.109.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.11.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.11.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.11.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.110.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.110.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.110.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.111.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.111.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.111.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.112.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.112.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.112.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.113.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.113.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.113.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.114.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.114.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.114.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.115.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.115.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.115.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.116.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.116.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.116.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.117.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.117.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.117.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.118.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.118.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.118.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.119.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.119.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.119.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.12.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.12.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.12.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.120.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.120.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.120.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.121.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.121.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.121.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.122.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.122.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.122.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.123.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.123.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.123.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.124.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.124.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.124.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.125.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.125.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.125.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.126.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.126.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.126.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.127.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.127.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.127.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.13.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.13.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.13.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.14.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.14.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.14.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.15.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.15.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.15.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.16.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.16.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.16.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.17.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.17.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.17.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.18.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.18.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.18.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.19.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.19.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.19.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.2.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.2.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.2.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.20.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.20.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.20.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.21.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.21.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.21.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.22.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.22.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.22.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.23.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.23.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.23.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.24.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.24.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.24.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.25.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.25.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.25.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.26.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.26.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.26.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.27.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.27.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.27.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.28.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.28.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.28.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.29.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.29.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.29.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.3.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.3.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.3.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.30.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.30.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.30.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.31.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.31.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.31.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.32.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.32.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.32.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.33.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.33.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.33.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.34.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.34.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.34.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.35.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.35.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.35.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.36.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.36.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.36.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.37.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.37.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.37.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.38.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.38.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.38.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.39.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.39.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.39.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.4.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.4.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.4.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.40.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.40.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.40.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.41.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.41.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.41.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.42.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.42.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.42.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.43.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.43.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.43.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.44.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.44.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.44.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.45.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.45.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.45.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.46.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.46.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.46.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.47.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.47.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.47.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.48.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.48.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.48.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.49.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.49.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.49.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.5.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.5.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.5.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.50.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.50.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.50.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.51.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.51.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.51.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.52.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.52.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.52.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.53.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.53.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.53.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.54.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.54.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.54.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.55.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.55.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.55.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.56.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.56.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.56.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.57.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.57.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.57.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.58.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.58.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.58.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.59.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.59.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.59.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.6.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.6.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.6.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.60.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.60.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.60.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.61.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.61.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.61.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.62.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.62.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.62.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.63.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.63.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.63.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.64.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.64.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.64.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.65.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.65.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.65.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.66.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.66.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.66.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.67.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.67.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.67.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.68.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.68.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.68.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.69.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.69.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.69.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.7.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.7.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.7.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.70.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.70.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.70.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.71.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.71.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.71.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.72.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.72.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.72.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.73.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.73.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.73.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.74.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.74.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.74.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.75.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.75.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.75.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.76.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.76.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.76.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.77.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.77.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.77.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.78.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.78.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.78.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.79.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.79.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.79.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.8.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.8.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.8.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.80.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.80.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.80.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.81.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.81.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.81.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.82.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.82.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.82.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.83.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.83.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.83.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.84.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.84.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.84.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.85.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.85.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.85.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.86.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.86.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.86.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.87.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.87.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.87.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.88.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.88.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.88.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.89.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.89.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.89.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.9.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.9.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.9.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.90.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.90.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.90.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.91.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.91.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.91.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.92.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.92.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.92.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.93.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.93.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.93.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.94.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.94.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.94.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.95.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.95.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.95.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.96.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.96.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.96.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.97.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.97.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.97.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.98.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.98.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.98.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.99.down_proj.weight": "model-00006-of-00049.safetensors", + "model.layers.6.mlp.experts.99.gate_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.experts.99.up_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.mlp.gate.weight": "model-00007-of-00049.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.input_layernorm.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.0.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.0.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.0.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.1.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.1.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.1.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.10.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.10.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.10.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.100.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.100.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.100.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.101.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.101.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.101.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.102.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.102.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.102.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.103.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.103.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.103.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.104.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.104.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.104.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.105.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.105.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.105.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.106.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.106.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.106.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.107.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.107.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.107.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.108.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.108.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.108.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.109.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.109.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.109.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.11.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.11.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.11.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.110.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.110.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.110.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.111.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.111.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.111.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.112.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.112.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.112.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.113.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.113.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.113.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.114.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.114.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.114.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.115.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.115.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.115.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.116.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.116.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.116.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.117.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.117.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.117.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.118.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.118.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.118.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.119.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.119.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.119.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.12.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.12.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.12.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.120.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.120.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.120.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.121.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.121.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.121.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.122.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.122.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.122.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.123.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.123.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.123.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.124.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.124.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.124.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.125.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.125.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.125.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.126.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.126.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.126.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.127.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.127.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.127.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.13.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.13.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.13.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.14.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.14.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.14.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.15.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.15.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.15.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.16.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.16.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.16.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.17.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.17.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.17.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.18.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.18.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.18.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.19.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.19.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.19.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.2.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.2.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.2.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.20.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.20.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.20.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.21.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.21.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.21.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.22.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.22.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.22.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.23.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.23.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.23.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.24.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.24.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.24.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.25.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.25.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.25.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.26.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.26.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.26.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.27.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.27.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.27.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.28.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.28.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.28.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.29.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.29.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.29.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.3.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.3.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.3.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.30.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.30.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.30.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.31.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.31.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.31.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.32.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.32.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.32.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.33.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.33.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.33.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.34.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.34.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.34.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.35.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.35.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.35.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.36.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.36.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.36.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.37.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.37.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.37.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.38.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.38.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.38.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.39.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.39.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.39.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.4.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.4.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.4.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.40.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.40.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.40.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.41.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.41.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.41.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.42.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.42.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.42.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.43.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.43.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.43.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.44.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.44.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.44.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.45.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.45.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.45.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.46.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.46.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.46.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.47.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.47.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.47.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.48.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.48.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.48.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.49.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.49.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.49.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.5.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.5.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.5.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.50.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.50.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.50.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.51.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.51.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.51.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.52.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.52.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.52.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.53.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.53.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.53.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.54.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.54.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.54.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.55.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.55.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.55.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.56.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.56.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.56.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.57.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.57.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.57.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.58.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.58.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.58.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.59.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.59.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.59.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.6.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.6.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.6.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.60.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.60.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.60.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.61.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.61.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.61.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.62.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.62.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.62.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.63.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.63.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.63.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.64.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.64.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.64.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.65.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.65.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.65.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.66.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.66.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.66.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.67.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.67.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.67.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.68.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.68.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.68.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.69.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.69.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.69.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.7.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.7.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.7.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.70.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.70.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.70.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.71.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.71.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.71.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.72.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.72.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.72.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.73.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.73.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.73.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.74.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.74.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.74.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.75.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.75.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.75.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.76.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.76.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.76.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.77.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.77.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.77.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.78.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.78.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.78.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.79.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.79.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.79.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.8.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.8.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.8.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.80.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.80.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.80.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.81.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.81.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.81.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.82.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.82.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.82.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.83.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.83.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.83.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.84.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.84.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.84.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.85.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.85.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.85.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.86.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.86.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.86.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.87.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.87.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.87.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.88.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.88.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.88.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.89.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.89.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.89.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.9.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.9.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.9.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.90.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.90.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.90.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.91.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.91.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.91.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.92.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.92.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.92.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.93.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.93.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.93.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.94.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.94.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.94.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.95.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.95.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.95.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.96.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.96.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.96.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.97.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.97.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.97.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.98.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.98.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.98.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.99.down_proj.weight": "model-00007-of-00049.safetensors", + "model.layers.7.mlp.experts.99.gate_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.experts.99.up_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.mlp.gate.weight": "model-00008-of-00049.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.input_layernorm.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.0.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.0.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.0.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.1.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.1.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.1.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.10.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.10.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.10.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.100.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.100.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.100.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.101.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.101.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.101.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.102.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.102.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.102.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.103.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.103.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.103.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.104.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.104.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.104.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.105.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.105.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.105.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.106.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.106.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.106.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.107.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.107.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.107.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.108.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.108.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.108.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.109.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.109.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.109.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.11.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.11.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.11.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.110.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.110.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.110.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.111.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.111.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.111.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.112.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.112.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.112.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.113.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.113.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.113.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.114.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.114.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.114.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.115.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.115.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.115.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.116.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.116.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.116.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.117.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.117.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.117.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.118.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.118.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.118.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.119.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.119.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.119.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.12.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.12.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.12.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.120.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.120.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.120.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.121.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.121.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.121.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.122.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.122.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.122.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.123.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.123.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.123.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.124.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.124.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.124.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.125.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.125.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.125.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.126.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.126.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.126.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.127.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.127.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.127.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.13.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.13.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.13.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.14.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.14.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.14.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.15.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.15.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.15.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.16.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.16.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.16.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.17.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.17.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.17.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.18.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.18.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.18.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.19.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.19.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.19.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.2.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.2.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.2.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.20.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.20.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.20.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.21.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.21.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.21.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.22.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.22.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.22.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.23.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.23.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.23.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.24.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.24.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.24.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.25.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.25.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.25.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.26.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.26.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.26.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.27.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.27.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.27.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.28.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.28.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.28.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.29.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.29.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.29.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.3.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.3.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.3.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.30.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.30.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.30.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.31.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.31.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.31.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.32.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.32.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.32.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.33.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.33.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.33.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.34.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.34.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.34.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.35.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.35.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.35.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.36.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.36.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.36.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.37.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.37.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.37.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.38.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.38.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.38.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.39.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.39.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.39.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.4.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.4.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.4.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.40.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.40.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.40.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.41.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.41.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.41.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.42.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.42.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.42.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.43.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.43.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.43.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.44.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.44.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.44.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.45.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.45.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.45.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.46.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.46.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.46.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.47.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.47.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.47.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.48.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.48.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.48.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.49.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.49.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.49.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.5.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.5.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.5.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.50.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.50.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.50.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.51.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.51.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.51.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.52.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.52.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.52.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.53.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.53.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.53.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.54.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.54.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.54.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.55.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.55.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.55.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.56.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.56.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.56.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.57.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.57.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.57.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.58.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.58.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.58.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.59.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.59.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.59.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.6.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.6.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.6.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.60.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.60.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.60.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.61.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.61.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.61.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.62.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.62.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.62.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.63.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.63.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.63.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.64.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.64.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.64.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.65.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.65.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.65.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.66.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.66.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.66.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.67.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.67.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.67.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.68.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.68.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.68.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.69.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.69.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.69.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.7.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.7.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.7.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.70.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.70.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.70.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.71.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.71.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.71.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.72.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.72.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.72.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.73.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.73.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.73.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.74.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.74.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.74.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.75.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.75.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.75.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.76.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.76.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.76.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.77.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.77.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.77.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.78.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.78.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.78.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.79.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.79.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.79.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.8.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.8.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.8.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.80.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.80.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.80.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.81.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.81.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.81.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.82.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.82.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.82.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.83.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.83.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.83.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.84.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.84.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.84.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.85.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.85.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.85.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.86.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.86.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.86.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.87.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.87.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.87.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.88.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.88.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.88.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.89.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.89.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.89.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.9.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.9.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.9.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.90.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.90.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.90.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.91.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.91.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.91.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.92.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.92.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.92.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.93.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.93.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.93.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.94.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.94.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.94.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.95.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.95.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.95.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.96.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.96.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.96.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.97.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.97.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.97.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.98.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.98.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.98.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.99.down_proj.weight": "model-00008-of-00049.safetensors", + "model.layers.8.mlp.experts.99.gate_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.experts.99.up_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.mlp.gate.weight": "model-00009-of-00049.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.input_layernorm.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.0.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.0.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.0.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.1.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.1.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.1.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.10.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.10.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.10.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.100.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.100.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.100.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.101.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.101.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.101.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.102.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.102.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.102.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.103.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.103.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.103.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.104.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.104.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.104.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.105.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.105.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.105.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.106.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.106.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.106.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.107.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.107.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.107.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.108.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.108.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.108.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.109.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.109.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.109.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.11.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.11.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.11.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.110.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.110.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.110.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.111.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.111.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.111.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.112.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.112.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.112.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.113.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.113.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.113.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.114.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.114.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.114.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.115.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.115.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.115.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.116.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.116.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.116.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.117.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.117.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.117.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.118.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.118.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.118.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.119.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.119.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.119.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.12.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.12.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.12.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.120.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.120.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.120.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.121.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.121.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.121.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.122.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.122.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.122.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.123.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.123.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.123.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.124.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.124.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.124.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.125.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.125.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.125.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.126.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.126.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.126.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.127.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.127.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.127.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.13.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.13.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.13.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.14.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.14.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.14.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.15.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.15.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.15.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.16.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.16.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.16.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.17.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.17.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.17.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.18.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.18.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.18.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.19.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.19.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.19.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.2.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.2.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.2.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.20.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.20.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.20.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.21.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.21.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.21.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.22.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.22.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.22.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.23.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.23.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.23.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.24.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.24.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.24.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.25.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.25.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.25.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.26.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.26.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.26.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.27.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.27.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.27.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.28.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.28.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.28.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.29.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.29.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.29.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.3.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.3.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.3.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.30.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.30.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.30.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.31.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.31.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.31.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.32.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.32.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.32.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.33.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.33.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.33.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.34.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.34.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.34.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.35.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.35.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.35.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.36.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.36.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.36.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.37.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.37.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.37.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.38.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.38.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.38.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.39.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.39.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.39.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.4.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.4.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.4.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.40.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.40.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.40.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.41.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.41.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.41.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.42.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.42.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.42.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.43.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.43.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.43.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.44.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.44.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.44.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.45.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.45.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.45.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.46.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.46.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.46.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.47.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.47.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.47.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.48.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.48.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.48.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.49.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.49.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.49.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.5.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.5.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.5.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.50.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.50.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.50.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.51.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.51.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.51.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.52.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.52.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.52.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.53.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.53.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.53.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.54.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.54.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.54.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.55.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.55.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.55.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.56.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.56.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.56.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.57.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.57.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.57.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.58.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.58.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.58.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.59.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.59.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.59.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.6.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.6.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.6.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.60.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.60.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.60.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.61.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.61.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.61.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.62.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.62.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.62.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.63.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.63.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.63.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.64.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.64.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.64.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.65.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.65.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.65.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.66.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.66.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.66.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.67.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.67.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.67.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.68.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.68.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.68.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.69.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.69.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.69.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.7.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.7.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.7.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.70.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.70.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.70.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.71.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.71.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.71.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.72.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.72.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.72.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.73.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.73.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.73.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.74.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.74.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.74.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.75.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.75.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.75.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.76.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.76.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.76.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.77.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.77.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.77.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.78.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.78.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.78.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.79.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.79.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.79.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.8.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.8.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.8.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.80.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.80.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.80.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.81.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.81.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.81.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.82.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.82.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.82.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.83.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.83.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.83.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.84.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.84.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.84.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.85.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.85.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.85.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.86.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.86.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.86.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.87.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.87.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.87.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.88.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.88.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.88.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.89.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.89.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.89.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.9.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.9.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.9.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.90.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.90.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.90.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.91.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.91.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.91.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.92.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.92.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.92.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.93.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.93.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.93.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.94.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.94.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.94.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.95.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.95.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.95.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.96.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.96.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.96.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.97.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.97.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.97.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.98.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.98.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.98.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.99.down_proj.weight": "model-00009-of-00049.safetensors", + "model.layers.9.mlp.experts.99.gate_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.experts.99.up_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.mlp.gate.weight": "model-00010-of-00049.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00049.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00010-of-00049.safetensors", + "model.norm.weight": "model-00049-of-00049.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..7d90b1a7abc0c8c5e3da8c11d6aab610a7a8dea0 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,30 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|END_OF_TURN_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} \ No newline at end of file diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..20c4bef669a2bcaa378342d1d2551ae10c352c7d --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14bd1c49d7d11874921d324986713df4be21cd06060530c497dacef99919b7a5 +size 28217141 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..04d772a5bfd8e0dc6f7e701ea0fbaa7a3b80eba0 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,328 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": false, + "clean_up_tokenization_spaces": false, + "legacy": true, + "spaces_between_special_tokens": false, + "use_default_system_prompt": false, + "bos_token": "", + "eos_token": "<|END_OF_TURN_TOKEN|>", + "pad_token": "", + "unk_token": "", + "tokenizer_class": "TokenizersBackend", + "model_max_length": 1000000000000000019884624838656, + "sp_model_kwargs": {}, + "chat_template": [ + { + "name": "default", + "template": "{{ bos_token }}{% if documents %}\n{% set tools = [] %}\n{%- macro document_turn(documents) -%}\n{# format documents into chat turn #}\n<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_THINKING|>I will look through the document to address the users needs.<|END_THINKING|><|START_ACTION|>[\n {\"tool_call_id\": \"0\", \"tool_name\": \"direct-injected-document\", \"parameters\": {}}\n]<|END_ACTION|><|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|START_TOOL_RESULT|>[\n {\n \"tool_call_id\": \"0\",\n \"results\": {\n{% for doc in documents %}\n \"{{ loop.index0 }}\": {{doc|tojson}}{% if not loop.last %},\n {% endif %}\n{% endfor %}\n\n },\n \"is_error\": null\n }\n]<|END_TOOL_RESULT|><|END_OF_TURN_TOKEN|>{%- endmacro %}\n{%- macro tool_call_id_to_int(messages, tool_call_id) %}\n{%- set counter = namespace(value=0) %}\n{%- set tool_call_id_seen = namespace(value=false) %}\n{%- for msg in messages %}\n {%- if msg.tool_calls %}\n {%- for tool_call in msg.tool_calls %}\n {%- if tool_call.id == tool_call_id and not tool_call_id_seen.value -%}\n {{ counter.value }}\n {%- set tool_call_id_seen.value = true %}\n {%- endif %}\n {%- set counter.value = counter.value + 1 %}\n {%- endfor %}\n {%- endif %}\n{%- endfor %}\n{%- endmacro %}\n{%- macro format_tool_message(messages, tool_msg) -%}\n{# format tool message #}\n {\n \"tool_call_id\": \"{{ tool_call_id_to_int(messages, tool_msg.tool_call_id) }}\",\n \"results\": {\n \"0\": {{ tool_msg.content|tojson }}\n },\n \"is_error\": null\n }\n{%- endmacro -%}\n{%- if messages and messages[0]['role']|lower == 'system' %}{%- set developer_preamble = messages[0]['content'] %}{% endif %}\n{%- set tool_idx = namespace(value=0) %}\n{%- set tool_ids_seen = namespace(value=[]) %}\n{%- set sent_documents = namespace(value=false) %}\n<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|># System Preamble\nYou are in contextual safety mode. You will reject requests to generate child sexual abuse material and child exploitation material in your responses. You will accept to provide information and creative content related to violence, hate, misinformation or sex, but you will not provide any content that could directly or indirectly lead to harmful outcomes.\n\nYour information cutoff date is June 2024.\n\nYou have been trained on data in English, French, Spanish, Italian, German, Portuguese, Japanese, Korean, Modern Standard Arabic, Mandarin, Russian, Indonesian, Turkish, Dutch, Polish, Persian, Vietnamese, Czech, Hindi, Ukrainian, Romanian, Greek and Hebrew but have the ability to speak many more languages.\n{% if tools or documents %}\n\nYou have been trained to have advanced reasoning and tool-use capabilities and you should make best use of these skills to serve user's requests.\n\n## Tool Use\nThink about how you can make best use of the provided tools to help with the task and come up with a high level plan that you will execute first.\n\n0. Start by writing <|START_THINKING|> followed by a detailed step by step plan of how you will solve the problem. For each step explain your thinking fully and give details of required tool calls (if needed). Unless specified otherwise, you write your plan in natural language. When you finish, close it out with <|END_THINKING|>.\n You can optionally choose to skip this step when the user request is so straightforward to address that only a trivial plan would be needed.\n NOTE: You MUST skip this step when you are directly responding to the user's request without using any tools.\n\nThen carry out your plan by repeatedly executing the following steps.\n1. Action: write <|START_ACTION|> followed by a list of JSON-formatted tool calls, with each one containing \"tool_name\" and \"parameters\" fields.\n When there are multiple tool calls which are completely independent of each other (i.e. they can be executed in parallel), you should list them out all together in one step. When you finish, close it out with <|END_ACTION|>.\n2. Observation: you will then receive results of those tool calls in JSON format in the very next turn, wrapped around by <|START_TOOL_RESULT|> and <|END_TOOL_RESULT|>. Carefully observe those results and think about what to do next. Note that these results will be provided to you in a separate turn. NEVER hallucinate results.\n Every tool call produces a list of results (when a tool call produces no result or a single result, it'll still get wrapped inside a list). Each result is clearly linked to its originating tool call via its \"tool_call_id\".\n3. Reflection: start the next turn by writing <|START_THINKING|> followed by what you've figured out so far, any changes you need to make to your plan, and what you will do next. When you finish, close it out with <|END_THINKING|>.\n You can optionally choose to skip this step when everything is going according to plan and no special pieces of information or reasoning chains need to be recorded.\n NOTE: You MUST skip this step when you are done with tool-use actions and are ready to respond to the user.\n\nYou can repeat the above 3 steps multiple times (could be 0 times too if no suitable tool calls are available or needed), until you decide it's time to finally respond to the user.\n\n4. Response: then break out of the loop and write <|START_RESPONSE|> followed by a piece of text which serves as a response to the user's last request. Use all previous tool calls and results to help you when formulating your response. When you finish, close it out with <|END_RESPONSE|>.\n{% if enable_citations %}\n\n## Grounding\nImportantly, note that \"Reflection\" and \"Response\" above can be grounded.\nGrounding means you associate pieces of texts (called \"spans\") with those specific tool results that support them (called \"sources\"). And you use a pair of tags \"\" and \"\" to indicate when a span can be grounded onto a list of sources, listing them out in the closing tag. Sources from the same tool call are grouped together and listed as \"{tool_call_id}:[{list of result indices}]\", before they are joined together by \",\". E.g., \"span\" means that \"span\" is supported by result 1 and 2 from \"tool_call_id=0\" as well as result 0 from \"tool_call_id=1\".\n{% endif %}\n\n## Available Tools\nHere is the list of tools that you have available to you.\nYou can ONLY use the tools listed here. When a tool is not listed below, it is NOT available and you should NEVER attempt to use it.\nEach tool is represented as a JSON object with fields like \"name\", \"description\", \"parameters\" (per JSON Schema), and optionally, \"responses\" (per JSON Schema).\n\n```json\n[\n{% if documents %}\n {\"name\": \"direct-injected-document\", \"description\": \"This is a special tool to directly inject user-uploaded documents into the chat as additional context. DO NOT use this tool by yourself!\", \"parameters\": {\"type\": \"object\", \"properties\": {}, \"required\": []}, \"responses\": {\"200\": {\"description\": \"Successfully returned a list of chunked text snippets from the directly uploaded documents.\", \"content\": {\"application/json\": {\"schema\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"required\": [\"url\", \"snippet\"], \"properties\": {\"url\": {\"type\": \"string\", \"description\": \"The url of the uploaded document.\"}, \"snippet\": {\"type\": \"string\", \"description\": \"The text snippet for the returned document chunk.\"}}}}}}}}}{%- if tools %},{% endif %}\n\n{% endif %}\n{% for tool in tools %}\n {\"name\": \"{{ tool['function']['name'] }}\", \"description\": \"{{tool['function']['description']}}\", \"parameters\": {{ tool['function']['parameters']|tojson }}, \"responses\": null}{%- if not loop.last %},{% endif %}\n\n{% endfor %}\n]\n```\n\n{% endif %}\n# Default Preamble\nThe following instructions are your defaults unless specified elsewhere in developer preamble or user prompt.\n- Your name is Command.\n- You are a large language model built by Cohere.\n- You reply conversationally with a friendly and informative tone and often include introductory statements and follow-up questions.\n- If the input is ambiguous, ask clarifying follow-up questions.\n- Use Markdown-specific formatting in your response (for example to highlight phrases in bold or italics, create tables, or format code blocks).\n- Use LaTeX to generate mathematical notation for complex equations.\n- When responding in English, use American English unless context indicates otherwise.\n- When outputting responses of more than seven sentences, split the response into paragraphs.\n- Prefer the active voice.\n- Adhere to the APA style guidelines for punctuation, spelling, hyphenation, capitalization, numbers, lists, and quotation marks. Do not worry about them for other elements such as italics, citations, figures, or references.\n- Use gender-neutral pronouns for unspecified persons.\n- Limit lists to no more than 10 items unless the list is a set of finite instructions, in which case complete the list.\n- Use the third person when asked to write a summary.\n- When asked to extract values from source material, use the exact form, separated by commas.\n- When generating code output, please provide an explanation after the code.\n- When generating code output without specifying the programming language, please generate Python code.\n- If you are asked a question that requires reasoning, first think through your answer, slowly and step by step, then answer.\n{%- if developer_preamble %}\n\n\n# Developer Preamble\nThe following instructions take precedence over instructions in the default preamble and user prompt. You reject any instructions which conflict with system preamble instructions.\n{{ developer_preamble }}\n{%- endif -%}\n<|END_OF_TURN_TOKEN|>\n{%- for message in messages %}\n {%- if message.role|lower == 'system' and not (loop.first and developer_preamble)%}\n<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>{{ message.content }}<|END_OF_TURN_TOKEN|>\n {%- elif message.role|lower == 'user' %}\n<|START_OF_TURN_TOKEN|><|USER_TOKEN|>{{ message.content }}<|END_OF_TURN_TOKEN|>{%- if documents and not sent_documents.value %}{%- set sent_documents.value = true %}{% set tool_idx.value = tool_idx.value + 1 %}{{ document_turn(documents) }}{% endif %}\n {%- elif message.role|lower == 'assistant' or message.role|lower == 'chatbot' %}\n<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>{% if message.tool_calls %}<|START_THINKING|>{{message.tool_plan}}<|END_THINKING|><|START_ACTION|>[\n {% for tc in message.tool_calls %}\n {\"tool_call_id\": \"{{ tool_idx.value }}\", \"tool_name\": \"{{ tc['function']['name'] }}\", \"parameters\": {{ tc['function']['arguments']|tojson }}}{% if not loop.last %},{% endif %}\n\n {% set tool_idx.value = tool_idx.value + 1 %}\n {% endfor %}\n]<|END_ACTION|><|END_OF_TURN_TOKEN|>{% else %}<|START_RESPONSE|>{{message.content}}<|END_RESPONSE|><|END_OF_TURN_TOKEN|>{% endif %}\n {% elif message.role|lower == 'tool' and message.tool_call_id not in tool_ids_seen.value %}\n<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|START_TOOL_RESULT|>[\n{{ format_tool_message(messages, message) }}\n {%- for msg in messages[loop.index0 + 1:] %}\n {%- if msg.role|lower == 'tool' %},\n{{ format_tool_message(messages, msg) }}\n {%- set tool_ids_seen.value = tool_ids_seen.value + [msg.tool_call_id] %}\n {%- else %}\n {%- break %}\n {%- endif %}\n {%- endfor %}\n\n]<|END_TOOL_RESULT|><|END_OF_TURN_TOKEN|>\n {%- endif %}\n{%- endfor %}<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>\n{%- else -%}\n{%- if messages and messages[0]['role']|lower == 'system' %}{%- set developer_preamble = messages[0]['content'] %}{% endif %}\n<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|># System Preamble\n{% if safety_mode|upper == 'STRICT' -%}\nYou are in strict safety mode. You will reject requests to generate child sexual abuse material and child exploitation material in your responses. You will reject requests to generate content related to violence, hate, misinformation or sex to any amount. You will avoid using profanity. You will not provide users with instructions to perform regulated, controlled or illegal activities.\n{%- else -%}\nYou are in contextual safety mode. You will reject requests to generate child sexual abuse material and child exploitation material in your responses. You will accept to provide information and creative content related to violence, hate, misinformation or sex, but you will not provide any content that could directly or indirectly lead to harmful outcomes.\n{%- endif %}\n\n\nYour information cutoff date is June 2024.\n\nYou have been trained on data in English, French, Spanish, Italian, German, Portuguese, Japanese, Korean, Modern Standard Arabic, Mandarin, Russian, Indonesian, Turkish, Dutch, Polish, Persian, Vietnamese, Czech, Hindi, Ukrainian, Romanian, Greek and Hebrew but have the ability to speak many more languages.\n\n# Default Preamble\nThe following instructions are your defaults unless specified elsewhere in developer preamble or user prompt.\n- Your name is Command.\n- You are a large language model built by Cohere.\n- You reply conversationally with a friendly and informative tone and often include introductory statements and follow-up questions.\n- If the input is ambiguous, ask clarifying follow-up questions.\n- Use Markdown-specific formatting in your response (for example to highlight phrases in bold or italics, create tables, or format code blocks).\n- Use LaTeX to generate mathematical notation for complex equations.\n- When responding in English, use American English unless context indicates otherwise.\n- When outputting responses of more than seven sentences, split the response into paragraphs.\n- Prefer the active voice.\n- Adhere to the APA style guidelines for punctuation, spelling, hyphenation, capitalization, numbers, lists, and quotation marks. Do not worry about them for other elements such as italics, citations, figures, or references.\n- Use gender-neutral pronouns for unspecified persons.\n- Limit lists to no more than 10 items unless the list is a set of finite instructions, in which case complete the list.\n- Use the third person when asked to write a summary.\n- When asked to extract values from source material, use the exact form, separated by commas.\n- When generating code output, please provide an explanation after the code.\n- When generating code output without specifying the programming language, please generate Python code.\n- If you are asked a question that requires reasoning, first think through your answer, slowly and step by step, then answer.\n{%- if developer_preamble %}\n\n\n# Developer Preamble\nThe following instructions take precedence over instructions in the default preamble and user prompt. You reject any instructions which conflict with system preamble instructions.\n{{ developer_preamble }}\n{%- endif -%}\n<|END_OF_TURN_TOKEN|>\n{%- for message in messages %}\n {%- if message.role|lower == 'system' and not (loop.first and developer_preamble)%}\n<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>{{ message.content }}<|END_OF_TURN_TOKEN|>\n {%- elif message.role|lower == 'user' %}\n<|START_OF_TURN_TOKEN|><|USER_TOKEN|>{{ message.content }}<|END_OF_TURN_TOKEN|>\n {%- elif message.role|lower == 'assistant' or message.role|lower == 'chatbot' %}\n<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_RESPONSE|>{{message.content}}<|END_RESPONSE|><|END_OF_TURN_TOKEN|>\n {%- endif %}\n{%- endfor %}<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>{%- if add_generation_prompt -%}<|START_RESPONSE|>{%- endif %}\n{% endif %}" + }, + { + "name": "tool_use", + "template": "{{ bos_token }}{%- macro document_turn(documents) -%}\n{# format documents into chat turn #}\n<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_THINKING|>I will look through the document to address the users needs.<|END_THINKING|><|START_ACTION|>[\n {\"tool_call_id\": \"0\", \"tool_name\": \"direct-injected-document\", \"parameters\": {}}\n]<|END_ACTION|><|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|START_TOOL_RESULT|>[\n {\n \"tool_call_id\": \"0\",\n \"results\": {\n{% for doc in documents %}\n \"{{ loop.index0 }}\": {{doc|tojson}}{% if not loop.last %},\n {% endif %}\n{% endfor %}\n\n },\n \"is_error\": null\n }\n]<|END_TOOL_RESULT|><|END_OF_TURN_TOKEN|>{%- endmacro %}\n{%- macro tool_call_id_to_int(messages, tool_call_id) %}\n{%- set counter = namespace(value=0) %}\n{%- set tool_call_id_seen = namespace(value=false) %}\n{%- for msg in messages %}\n {%- if msg.tool_calls %}\n {%- for tool_call in msg.tool_calls %}\n {%- if tool_call.id == tool_call_id and not tool_call_id_seen.value -%}\n {{ counter.value }}\n {%- set tool_call_id_seen.value = true %}\n {%- endif %}\n {%- set counter.value = counter.value + 1 %}\n {%- endfor %}\n {%- endif %}\n{%- endfor %}\n{%- endmacro %}\n{%- macro format_tool_message(messages, tool_msg) -%}\n{# format tool message #}\n {\n \"tool_call_id\": \"{{ tool_call_id_to_int(messages, tool_msg.tool_call_id) }}\",\n \"results\": {\n \"0\": {{ tool_msg.content|tojson }}\n },\n \"is_error\": null\n }\n{%- endmacro -%}\n{%- if messages and messages[0]['role']|lower == 'system' %}{%- set developer_preamble = messages[0]['content'] %}{% endif %}\n{%- set tool_idx = namespace(value=0) %}\n{%- set tool_ids_seen = namespace(value=[]) %}\n{%- set sent_documents = namespace(value=false) %}\n<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|># System Preamble\nYou are in contextual safety mode. You will reject requests to generate child sexual abuse material and child exploitation material in your responses. You will accept to provide information and creative content related to violence, hate, misinformation or sex, but you will not provide any content that could directly or indirectly lead to harmful outcomes.\n\nYour information cutoff date is June 2024.\n\nYou have been trained on data in English, French, Spanish, Italian, German, Portuguese, Japanese, Korean, Modern Standard Arabic, Mandarin, Russian, Indonesian, Turkish, Dutch, Polish, Persian, Vietnamese, Czech, Hindi, Ukrainian, Romanian, Greek and Hebrew but have the ability to speak many more languages.\n{% if tools or documents %}\n\nYou have been trained to have advanced reasoning and tool-use capabilities and you should make best use of these skills to serve user's requests.\n\n## Tool Use\nThink about how you can make best use of the provided tools to help with the task and come up with a high level plan that you will execute first.\n\n0. Start by writing <|START_THINKING|> followed by a detailed step by step plan of how you will solve the problem. For each step explain your thinking fully and give details of required tool calls (if needed). Unless specified otherwise, you write your plan in natural language. When you finish, close it out with <|END_THINKING|>.\n You can optionally choose to skip this step when the user request is so straightforward to address that only a trivial plan would be needed.\n NOTE: You MUST skip this step when you are directly responding to the user's request without using any tools.\n\nThen carry out your plan by repeatedly executing the following steps.\n1. Action: write <|START_ACTION|> followed by a list of JSON-formatted tool calls, with each one containing \"tool_name\" and \"parameters\" fields.\n When there are multiple tool calls which are completely independent of each other (i.e. they can be executed in parallel), you should list them out all together in one step. When you finish, close it out with <|END_ACTION|>.\n2. Observation: you will then receive results of those tool calls in JSON format in the very next turn, wrapped around by <|START_TOOL_RESULT|> and <|END_TOOL_RESULT|>. Carefully observe those results and think about what to do next. Note that these results will be provided to you in a separate turn. NEVER hallucinate results.\n Every tool call produces a list of results (when a tool call produces no result or a single result, it'll still get wrapped inside a list). Each result is clearly linked to its originating tool call via its \"tool_call_id\".\n3. Reflection: start the next turn by writing <|START_THINKING|> followed by what you've figured out so far, any changes you need to make to your plan, and what you will do next. When you finish, close it out with <|END_THINKING|>.\n You can optionally choose to skip this step when everything is going according to plan and no special pieces of information or reasoning chains need to be recorded.\n NOTE: You MUST skip this step when you are done with tool-use actions and are ready to respond to the user.\n\nYou can repeat the above 3 steps multiple times (could be 0 times too if no suitable tool calls are available or needed), until you decide it's time to finally respond to the user.\n\n4. Response: then break out of the loop and write <|START_RESPONSE|> followed by a piece of text which serves as a response to the user's last request. Use all previous tool calls and results to help you when formulating your response. When you finish, close it out with <|END_RESPONSE|>.\n{% if enable_citations %}\n\n## Grounding\nImportantly, note that \"Reflection\" and \"Response\" above can be grounded.\nGrounding means you associate pieces of texts (called \"spans\") with those specific tool results that support them (called \"sources\"). And you use a pair of tags \"\" and \"\" to indicate when a span can be grounded onto a list of sources, listing them out in the closing tag. Sources from the same tool call are grouped together and listed as \"{tool_call_id}:[{list of result indices}]\", before they are joined together by \",\". E.g., \"span\" means that \"span\" is supported by result 1 and 2 from \"tool_call_id=0\" as well as result 0 from \"tool_call_id=1\".\n{% endif %}\n\n## Available Tools\nHere is the list of tools that you have available to you.\nYou can ONLY use the tools listed here. When a tool is not listed below, it is NOT available and you should NEVER attempt to use it.\nEach tool is represented as a JSON object with fields like \"name\", \"description\", \"parameters\" (per JSON Schema), and optionally, \"responses\" (per JSON Schema).\n\n```json\n[\n{% if documents %}\n {\"name\": \"direct-injected-document\", \"description\": \"This is a special tool to directly inject user-uploaded documents into the chat as additional context. DO NOT use this tool by yourself!\", \"parameters\": {\"type\": \"object\", \"properties\": {}, \"required\": []}, \"responses\": {\"200\": {\"description\": \"Successfully returned a list of chunked text snippets from the directly uploaded documents.\", \"content\": {\"application/json\": {\"schema\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"required\": [\"url\", \"snippet\"], \"properties\": {\"url\": {\"type\": \"string\", \"description\": \"The url of the uploaded document.\"}, \"snippet\": {\"type\": \"string\", \"description\": \"The text snippet for the returned document chunk.\"}}}}}}}}}{%- if tools %},{% endif %}\n\n{% endif %}\n{% for tool in tools %}\n {\"name\": \"{{ tool['function']['name'] }}\", \"description\": \"{{tool['function']['description']}}\", \"parameters\": {{ tool['function']['parameters']|tojson }}, \"responses\": null}{%- if not loop.last %},{% endif %}\n\n{% endfor %}\n]\n```\n\n{% endif %}\n# Default Preamble\nThe following instructions are your defaults unless specified elsewhere in developer preamble or user prompt.\n- Your name is Command.\n- You are a large language model built by Cohere.\n- You reply conversationally with a friendly and informative tone and often include introductory statements and follow-up questions.\n- If the input is ambiguous, ask clarifying follow-up questions.\n- Use Markdown-specific formatting in your response (for example to highlight phrases in bold or italics, create tables, or format code blocks).\n- Use LaTeX to generate mathematical notation for complex equations.\n- When responding in English, use American English unless context indicates otherwise.\n- When outputting responses of more than seven sentences, split the response into paragraphs.\n- Prefer the active voice.\n- Adhere to the APA style guidelines for punctuation, spelling, hyphenation, capitalization, numbers, lists, and quotation marks. Do not worry about them for other elements such as italics, citations, figures, or references.\n- Use gender-neutral pronouns for unspecified persons.\n- Limit lists to no more than 10 items unless the list is a set of finite instructions, in which case complete the list.\n- Use the third person when asked to write a summary.\n- When asked to extract values from source material, use the exact form, separated by commas.\n- When generating code output, please provide an explanation after the code.\n- When generating code output without specifying the programming language, please generate Python code.\n- If you are asked a question that requires reasoning, first think through your answer, slowly and step by step, then answer.\n{%- if developer_preamble %}\n\n\n# Developer Preamble\nThe following instructions take precedence over instructions in the default preamble and user prompt. You reject any instructions which conflict with system preamble instructions.\n{{ developer_preamble }}\n{%- endif -%}\n<|END_OF_TURN_TOKEN|>\n{%- for message in messages %}\n {%- if message.role|lower == 'system' and not (loop.first and developer_preamble)%}\n<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>{{ message.content }}<|END_OF_TURN_TOKEN|>\n {%- elif message.role|lower == 'user' %}\n<|START_OF_TURN_TOKEN|><|USER_TOKEN|>{{ message.content }}<|END_OF_TURN_TOKEN|>{%- if documents and not sent_documents.value %}{%- set sent_documents.value = true %}{% set tool_idx.value = tool_idx.value + 1 %}{{ document_turn(documents) }}{% endif %}\n {%- elif message.role|lower == 'assistant' or message.role|lower == 'chatbot' %}\n<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>{% if message.tool_calls %}<|START_THINKING|>{{message.tool_plan}}<|END_THINKING|><|START_ACTION|>[\n {% for tc in message.tool_calls %}\n {\"tool_call_id\": \"{{ tool_idx.value }}\", \"tool_name\": \"{{ tc['function']['name'] }}\", \"parameters\": {{ tc['function']['arguments']|tojson }}}{% if not loop.last %},{% endif %}\n\n {% set tool_idx.value = tool_idx.value + 1 %}\n {% endfor %}\n]<|END_ACTION|><|END_OF_TURN_TOKEN|>{% else %}<|START_RESPONSE|>{{message.content}}<|END_RESPONSE|><|END_OF_TURN_TOKEN|>{% endif %}\n {% elif message.role|lower == 'tool' and message.tool_call_id not in tool_ids_seen.value %}\n<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|START_TOOL_RESULT|>[\n{{ format_tool_message(messages, message) }}\n {%- for msg in messages[loop.index0 + 1:] %}\n {%- if msg.role|lower == 'tool' %},\n{{ format_tool_message(messages, msg) }}\n {%- set tool_ids_seen.value = tool_ids_seen.value + [msg.tool_call_id] %}\n {%- else %}\n {%- break %}\n {%- endif %}\n {%- endfor %}\n\n]<|END_TOOL_RESULT|><|END_OF_TURN_TOKEN|>\n {%- endif %}\n{%- endfor %}<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>" + }, + { + "name": "rag", + "template": "{{ bos_token }}{% set tools = [] %}\n{%- macro document_turn(documents) -%}\n{# format documents into chat turn #}\n<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_THINKING|>I will look through the document to address the users needs.<|END_THINKING|><|START_ACTION|>[\n {\"tool_call_id\": \"0\", \"tool_name\": \"direct-injected-document\", \"parameters\": {}}\n]<|END_ACTION|><|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|START_TOOL_RESULT|>[\n {\n \"tool_call_id\": \"0\",\n \"results\": {\n{% for doc in documents %}\n \"{{ loop.index0 }}\": {{doc|tojson}}{% if not loop.last %},\n {% endif %}\n{% endfor %}\n\n },\n \"is_error\": null\n }\n]<|END_TOOL_RESULT|><|END_OF_TURN_TOKEN|>{%- endmacro %}\n{%- macro tool_call_id_to_int(messages, tool_call_id) %}\n{%- set counter = namespace(value=0) %}\n{%- set tool_call_id_seen = namespace(value=false) %}\n{%- for msg in messages %}\n {%- if msg.tool_calls %}\n {%- for tool_call in msg.tool_calls %}\n {%- if tool_call.id == tool_call_id and not tool_call_id_seen.value -%}\n {{ counter.value }}\n {%- set tool_call_id_seen.value = true %}\n {%- endif %}\n {%- set counter.value = counter.value + 1 %}\n {%- endfor %}\n {%- endif %}\n{%- endfor %}\n{%- endmacro %}\n{%- macro format_tool_message(messages, tool_msg) -%}\n{# format tool message #}\n {\n \"tool_call_id\": \"{{ tool_call_id_to_int(messages, tool_msg.tool_call_id) }}\",\n \"results\": {\n \"0\": {{ tool_msg.content|tojson }}\n },\n \"is_error\": null\n }\n{%- endmacro -%}\n{%- if messages and messages[0]['role']|lower == 'system' %}{%- set developer_preamble = messages[0]['content'] %}{% endif %}\n{%- set tool_idx = namespace(value=0) %}\n{%- set tool_ids_seen = namespace(value=[]) %}\n{%- set sent_documents = namespace(value=false) %}\n<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|># System Preamble\nYou are in contextual safety mode. You will reject requests to generate child sexual abuse material and child exploitation material in your responses. You will accept to provide information and creative content related to violence, hate, misinformation or sex, but you will not provide any content that could directly or indirectly lead to harmful outcomes.\n\nYour information cutoff date is June 2024.\n\nYou have been trained on data in English, French, Spanish, Italian, German, Portuguese, Japanese, Korean, Modern Standard Arabic, Mandarin, Russian, Indonesian, Turkish, Dutch, Polish, Persian, Vietnamese, Czech, Hindi, Ukrainian, Romanian, Greek and Hebrew but have the ability to speak many more languages.\n{% if tools or documents %}\n\nYou have been trained to have advanced reasoning and tool-use capabilities and you should make best use of these skills to serve user's requests.\n\n## Tool Use\nThink about how you can make best use of the provided tools to help with the task and come up with a high level plan that you will execute first.\n\n0. Start by writing <|START_THINKING|> followed by a detailed step by step plan of how you will solve the problem. For each step explain your thinking fully and give details of required tool calls (if needed). Unless specified otherwise, you write your plan in natural language. When you finish, close it out with <|END_THINKING|>.\n You can optionally choose to skip this step when the user request is so straightforward to address that only a trivial plan would be needed.\n NOTE: You MUST skip this step when you are directly responding to the user's request without using any tools.\n\nThen carry out your plan by repeatedly executing the following steps.\n1. Action: write <|START_ACTION|> followed by a list of JSON-formatted tool calls, with each one containing \"tool_name\" and \"parameters\" fields.\n When there are multiple tool calls which are completely independent of each other (i.e. they can be executed in parallel), you should list them out all together in one step. When you finish, close it out with <|END_ACTION|>.\n2. Observation: you will then receive results of those tool calls in JSON format in the very next turn, wrapped around by <|START_TOOL_RESULT|> and <|END_TOOL_RESULT|>. Carefully observe those results and think about what to do next. Note that these results will be provided to you in a separate turn. NEVER hallucinate results.\n Every tool call produces a list of results (when a tool call produces no result or a single result, it'll still get wrapped inside a list). Each result is clearly linked to its originating tool call via its \"tool_call_id\".\n3. Reflection: start the next turn by writing <|START_THINKING|> followed by what you've figured out so far, any changes you need to make to your plan, and what you will do next. When you finish, close it out with <|END_THINKING|>.\n You can optionally choose to skip this step when everything is going according to plan and no special pieces of information or reasoning chains need to be recorded.\n NOTE: You MUST skip this step when you are done with tool-use actions and are ready to respond to the user.\n\nYou can repeat the above 3 steps multiple times (could be 0 times too if no suitable tool calls are available or needed), until you decide it's time to finally respond to the user.\n\n4. Response: then break out of the loop and write <|START_RESPONSE|> followed by a piece of text which serves as a response to the user's last request. Use all previous tool calls and results to help you when formulating your response. When you finish, close it out with <|END_RESPONSE|>.\n{% if enable_citations %}\n\n## Grounding\nImportantly, note that \"Reflection\" and \"Response\" above can be grounded.\nGrounding means you associate pieces of texts (called \"spans\") with those specific tool results that support them (called \"sources\"). And you use a pair of tags \"\" and \"\" to indicate when a span can be grounded onto a list of sources, listing them out in the closing tag. Sources from the same tool call are grouped together and listed as \"{tool_call_id}:[{list of result indices}]\", before they are joined together by \",\". E.g., \"span\" means that \"span\" is supported by result 1 and 2 from \"tool_call_id=0\" as well as result 0 from \"tool_call_id=1\".\n{% endif %}\n\n## Available Tools\nHere is the list of tools that you have available to you.\nYou can ONLY use the tools listed here. When a tool is not listed below, it is NOT available and you should NEVER attempt to use it.\nEach tool is represented as a JSON object with fields like \"name\", \"description\", \"parameters\" (per JSON Schema), and optionally, \"responses\" (per JSON Schema).\n\n```json\n[\n{% if documents %}\n {\"name\": \"direct-injected-document\", \"description\": \"This is a special tool to directly inject user-uploaded documents into the chat as additional context. DO NOT use this tool by yourself!\", \"parameters\": {\"type\": \"object\", \"properties\": {}, \"required\": []}, \"responses\": {\"200\": {\"description\": \"Successfully returned a list of chunked text snippets from the directly uploaded documents.\", \"content\": {\"application/json\": {\"schema\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"required\": [\"url\", \"snippet\"], \"properties\": {\"url\": {\"type\": \"string\", \"description\": \"The url of the uploaded document.\"}, \"snippet\": {\"type\": \"string\", \"description\": \"The text snippet for the returned document chunk.\"}}}}}}}}}{%- if tools %},{% endif %}\n\n{% endif %}\n{% for tool in tools %}\n {\"name\": \"{{ tool['function']['name'] }}\", \"description\": \"{{tool['function']['description']}}\", \"parameters\": {{ tool['function']['parameters']|tojson }}, \"responses\": null}{%- if not loop.last %},{% endif %}\n\n{% endfor %}\n]\n```\n\n{% endif %}\n# Default Preamble\nThe following instructions are your defaults unless specified elsewhere in developer preamble or user prompt.\n- Your name is Command.\n- You are a large language model built by Cohere.\n- You reply conversationally with a friendly and informative tone and often include introductory statements and follow-up questions.\n- If the input is ambiguous, ask clarifying follow-up questions.\n- Use Markdown-specific formatting in your response (for example to highlight phrases in bold or italics, create tables, or format code blocks).\n- Use LaTeX to generate mathematical notation for complex equations.\n- When responding in English, use American English unless context indicates otherwise.\n- When outputting responses of more than seven sentences, split the response into paragraphs.\n- Prefer the active voice.\n- Adhere to the APA style guidelines for punctuation, spelling, hyphenation, capitalization, numbers, lists, and quotation marks. Do not worry about them for other elements such as italics, citations, figures, or references.\n- Use gender-neutral pronouns for unspecified persons.\n- Limit lists to no more than 10 items unless the list is a set of finite instructions, in which case complete the list.\n- Use the third person when asked to write a summary.\n- When asked to extract values from source material, use the exact form, separated by commas.\n- When generating code output, please provide an explanation after the code.\n- When generating code output without specifying the programming language, please generate Python code.\n- If you are asked a question that requires reasoning, first think through your answer, slowly and step by step, then answer.\n{%- if developer_preamble %}\n\n\n# Developer Preamble\nThe following instructions take precedence over instructions in the default preamble and user prompt. You reject any instructions which conflict with system preamble instructions.\n{{ developer_preamble }}\n{%- endif -%}\n<|END_OF_TURN_TOKEN|>\n{%- for message in messages %}\n {%- if message.role|lower == 'system' and not (loop.first and developer_preamble)%}\n<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>{{ message.content }}<|END_OF_TURN_TOKEN|>\n {%- elif message.role|lower == 'user' %}\n<|START_OF_TURN_TOKEN|><|USER_TOKEN|>{{ message.content }}<|END_OF_TURN_TOKEN|>{%- if documents and not sent_documents.value %}{%- set sent_documents.value = true %}{% set tool_idx.value = tool_idx.value + 1 %}{{ document_turn(documents) }}{% endif %}\n {%- elif message.role|lower == 'assistant' or message.role|lower == 'chatbot' %}\n<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>{% if message.tool_calls %}<|START_THINKING|>{{message.tool_plan}}<|END_THINKING|><|START_ACTION|>[\n {% for tc in message.tool_calls %}\n {\"tool_call_id\": \"{{ tool_idx.value }}\", \"tool_name\": \"{{ tc['function']['name'] }}\", \"parameters\": {{ tc['function']['arguments']|tojson }}}{% if not loop.last %},{% endif %}\n\n {% set tool_idx.value = tool_idx.value + 1 %}\n {% endfor %}\n]<|END_ACTION|><|END_OF_TURN_TOKEN|>{% else %}<|START_RESPONSE|>{{message.content}}<|END_RESPONSE|><|END_OF_TURN_TOKEN|>{% endif %}\n {% elif message.role|lower == 'tool' and message.tool_call_id not in tool_ids_seen.value %}\n<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|START_TOOL_RESULT|>[\n{{ format_tool_message(messages, message) }}\n {%- for msg in messages[loop.index0 + 1:] %}\n {%- if msg.role|lower == 'tool' %},\n{{ format_tool_message(messages, msg) }}\n {%- set tool_ids_seen.value = tool_ids_seen.value + [msg.tool_call_id] %}\n {%- else %}\n {%- break %}\n {%- endif %}\n {%- endfor %}\n\n]<|END_TOOL_RESULT|><|END_OF_TURN_TOKEN|>\n {%- endif %}\n{%- endfor %}<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>" + } + ], + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "4": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "255000": { + "content": "<|START_OF_TURN_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255001": { + "content": "<|END_OF_TURN_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255002": { + "content": "<|USER_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255003": { + "content": "<|CHATBOT_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255004": { + "content": "<|SYSTEM_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255005": { + "content": "<|NEW_FILE|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "255006": { + "content": "<|BEGINNING_OF_PREFIX_FIM_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "255007": { + "content": "<|BEGINNING_OF_MIDDLE_FIM_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "255008": { + "content": "<|BEGINNING_OF_SUFFIX_FIM_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "255009": { + "content": "<|END_OF_MIDDLE_FIM_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "255010": { + "content": "<|START_THINKING|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255011": { + "content": "<|END_THINKING|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255012": { + "content": "<|START_TEXT|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255013": { + "content": "<|END_TEXT|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255014": { + "content": "<|START_ACTION|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255015": { + "content": "<|END_ACTION|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255016": { + "content": "<|START_TOOL_RESULT|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255017": { + "content": "<|END_TOOL_RESULT|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255018": { + "content": "<|USER_0_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255019": { + "content": "<|USER_1_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255020": { + "content": "<|USER_2_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255021": { + "content": "<|USER_3_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255022": { + "content": "<|USER_4_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255023": { + "content": "<|USER_5_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255024": { + "content": "<|USER_6_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255025": { + "content": "<|USER_7_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255026": { + "content": "<|USER_8_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255027": { + "content": "<|USER_9_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255028": { + "content": "<|START_OF_IMG|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "255029": { + "content": "<|END_OF_IMG|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "255030": { + "content": "<|IMG_LINE_BREAK|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "255031": { + "content": "<|IMG_PATCH|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + } +} \ No newline at end of file