diff --git a/.gitattributes b/.gitattributes index eaf8c1067aa7fbb96a52eb6b4962a7ce01b8e820..343c5e1d953128a8880957b56eeeb87a31f3294f 100644 --- a/.gitattributes +++ b/.gitattributes @@ -53,3 +53,6 @@ precise_coder/qwen35-4b-GRPO_0.5F1_min/global_step_300/actor/huggingface/tokeniz precise_coder/qwen35-4b-eagrpo_a0.8_b0.05/global_step_150/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text precise_coder/qwen35-4b-sftrl-rl_0.5f1/global_step_100/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text old_template_backup/precise_coder/qwen35-9b-GRPO_U/global_step_250/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +old_template_backup/precise_coder/qwen35-9b-eagrpo_a0.8_b0.05/global_step_200/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +old_template_backup/precise_coder/4b-SFT-dsv4pro-rl_0.5F1/global_step_250/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +old_template_backup/precise_coder/qwen35-9b-rl-strreplace/global_step_350/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/old_template_backup/precise_coder/4b-SFT-dsv4pro-rl_0.5F1/global_step_250/actor/fsdp_config.json b/old_template_backup/precise_coder/4b-SFT-dsv4pro-rl_0.5F1/global_step_250/actor/fsdp_config.json new file mode 100644 index 0000000000000000000000000000000000000000..17ff55630675ec23d6a1d79ec7a480aa25faa5de --- /dev/null +++ b/old_template_backup/precise_coder/4b-SFT-dsv4pro-rl_0.5F1/global_step_250/actor/fsdp_config.json @@ -0,0 +1,4 @@ +{ + "FSDP_version": 2, + "world_size": 4 +} \ No newline at end of file diff --git a/old_template_backup/precise_coder/4b-SFT-dsv4pro-rl_0.5F1/global_step_250/actor/huggingface/chat_template.jinja b/old_template_backup/precise_coder/4b-SFT-dsv4pro-rl_0.5F1/global_step_250/actor/huggingface/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..a585dec894e63da457d9440ec6aa7caa16d20860 --- /dev/null +++ b/old_template_backup/precise_coder/4b-SFT-dsv4pro-rl_0.5F1/global_step_250/actor/huggingface/chat_template.jinja @@ -0,0 +1,154 @@ +{%- set image_count = namespace(value=0) %} +{%- set video_count = namespace(value=0) %} +{%- macro render_content(content, do_vision_count, is_system_content=false) %} + {%- if content is string %} + {{- content }} + {%- elif content is iterable and content is not mapping %} + {%- for item in content %} + {%- if 'image' in item or 'image_url' in item or item.type == 'image' %} + {%- if is_system_content %} + {{- raise_exception('System message cannot contain images.') }} + {%- endif %} + {%- if do_vision_count %} + {%- set image_count.value = image_count.value + 1 %} + {%- endif %} + {%- if add_vision_id %} + {{- 'Picture ' ~ image_count.value ~ ': ' }} + {%- endif %} + {{- '<|vision_start|><|image_pad|><|vision_end|>' }} + {%- elif 'video' in item or item.type == 'video' %} + {%- if is_system_content %} + {{- raise_exception('System message cannot contain videos.') }} + {%- endif %} + {%- if do_vision_count %} + {%- set video_count.value = video_count.value + 1 %} + {%- endif %} + {%- if add_vision_id %} + {{- 'Video ' ~ video_count.value ~ ': ' }} + {%- endif %} + {{- '<|vision_start|><|video_pad|><|vision_end|>' }} + {%- elif 'text' in item %} + {{- item.text }} + {%- else %} + {{- raise_exception('Unexpected item type in content.') }} + {%- endif %} + {%- endfor %} + {%- elif content is none or content is undefined %} + {{- '' }} + {%- else %} + {{- raise_exception('Unexpected content type.') }} + {%- endif %} +{%- endmacro %} +{%- if not messages %} + {{- raise_exception('No messages provided.') }} +{%- endif %} +{%- if tools and tools is iterable and tools is not mapping %} + {{- '<|im_start|>system\n' }} + {{- "# Tools\n\nYou have access to the following functions:\n\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n" }} + {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n\n\n\nvalue_1\n\n\nThis is the value for the second parameter\nthat can span\nmultiple lines\n\n\n\n\n\nReminder:\n- Function calls MUST follow the specified format: an inner block must be nested within XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n' }} + {%- if messages[0].role == 'system' %} + {%- set content = render_content(messages[0].content, false, true)|trim %} + {%- if content %} + {{- '\n\n' + content }} + {%- endif %} + {%- endif %} + {{- '<|im_end|>\n' }} +{%- else %} + {%- if messages[0].role == 'system' %} + {%- set content = render_content(messages[0].content, false, true)|trim %} + {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} +{%- for message in messages[::-1] %} + {%- set index = (messages|length - 1) - loop.index0 %} + {%- if ns.multi_step_tool and message.role == "user" %} + {%- set content = render_content(message.content, false)|trim %} + {%- if not(content.startswith('') and content.endswith('')) %} + {%- set ns.multi_step_tool = false %} + {%- set ns.last_query_index = index %} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if ns.multi_step_tool %} + {{- raise_exception('No user query found in messages.') }} +{%- endif %} +{%- for message in messages %} + {%- set content = render_content(message.content, true)|trim %} + {%- if message.role == "system" %} + {%- if not loop.first %} + {{- raise_exception('System message must be at the beginning.') }} + {%- endif %} + {%- elif message.role == "user" %} + {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {%- set reasoning_content = '' %} + {%- if message.reasoning_content is string %} + {%- set reasoning_content = message.reasoning_content %} + {%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} + {%- endif %} + {%- set reasoning_content = reasoning_content|trim %} + {%- if loop.index0 > ns.last_query_index %} + {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content + '\n\n\n' + content }} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {%- if loop.first %} + {%- if content|trim %} + {{- '\n\n\n\n' }} + {%- else %} + {{- '\n\n' }} + {%- endif %} + {%- else %} + {{- '\n\n\n' }} + {%- endif %} + {%- if tool_call.arguments is defined %} + {%- for args_name, args_value in tool_call.arguments|items %} + {{- '\n' }} + {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %} + {{- args_value }} + {{- '\n\n' }} + {%- endfor %} + {%- endif %} + {{- '\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.previtem and loop.previtem.role != "tool" %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- content }} + {{- '\n' }} + {%- if not loop.last and loop.nextitem.role != "tool" %} + {{- '<|im_end|>\n' }} + {%- elif loop.last %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- else %} + {{- raise_exception('Unexpected message role.') }} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} + {%- if enable_thinking is defined and enable_thinking is false %} + {{- '\n\n\n\n' }} + {%- else %} + {{- '\n' }} + {%- endif %} +{%- endif %} \ No newline at end of file diff --git a/old_template_backup/precise_coder/4b-SFT-dsv4pro-rl_0.5F1/global_step_250/actor/huggingface/config.json b/old_template_backup/precise_coder/4b-SFT-dsv4pro-rl_0.5F1/global_step_250/actor/huggingface/config.json new file mode 100644 index 0000000000000000000000000000000000000000..0e8cd2d6f8b5c82e83b6479da2639aa4f7f24473 --- /dev/null +++ b/old_template_backup/precise_coder/4b-SFT-dsv4pro-rl_0.5F1/global_step_250/actor/huggingface/config.json @@ -0,0 +1,112 @@ +{ + "architectures": [ + "Qwen3_5ForConditionalGeneration" + ], + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 248046, + "image_token_id": 248056, + "model_type": "qwen3_5", + "pad_token_id": 248044, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "attn_output_gate": true, + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 248044, + "full_attention_interval": 4, + "head_dim": 256, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9216, + "layer_types": [ + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention" + ], + "linear_conv_kernel_dim": 4, + "linear_key_head_dim": 128, + "linear_num_key_heads": 16, + "linear_num_value_heads": 32, + "linear_value_head_dim": 128, + "mamba_ssm_dtype": "float32", + "max_position_embeddings": 262144, + "mlp_only_layers": [], + "model_type": "qwen3_5_text", + "mtp_num_hidden_layers": 0, + "mtp_use_dedicated_embeddings": false, + "num_attention_heads": 16, + "num_hidden_layers": 32, + "num_key_value_heads": 4, + "pad_token_id": null, + "partial_rotary_factor": 0.25, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "mrope_interleaved": true, + "mrope_section": [ + 11, + 11, + 10 + ], + "partial_rotary_factor": 0.25, + "rope_theta": 10000000, + "rope_type": "default" + }, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 248320 + }, + "tie_word_embeddings": true, + "transformers_version": "5.10.2", + "video_token_id": 248057, + "vision_config": { + "deepstack_visual_indexes": [], + "depth": 24, + "dtype": "bfloat16", + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1024, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 4096, + "model_type": "qwen3_5_vision", + "num_heads": 16, + "num_position_embeddings": 2304, + "out_hidden_size": 2560, + "patch_size": 16, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + }, + "vision_end_token_id": 248054, + "vision_start_token_id": 248053 +} diff --git a/old_template_backup/precise_coder/4b-SFT-dsv4pro-rl_0.5F1/global_step_250/actor/huggingface/generation_config.json b/old_template_backup/precise_coder/4b-SFT-dsv4pro-rl_0.5F1/global_step_250/actor/huggingface/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a8f50cfe9f041954a2175966a9ef6f88480f4769 --- /dev/null +++ b/old_template_backup/precise_coder/4b-SFT-dsv4pro-rl_0.5F1/global_step_250/actor/huggingface/generation_config.json @@ -0,0 +1,9 @@ +{ + "_from_model_config": true, + "eos_token_id": 248046, + "output_attentions": false, + "output_hidden_states": false, + "pad_token_id": 248044, + "transformers_version": "5.10.2", + "use_cache": true +} diff --git a/old_template_backup/precise_coder/4b-SFT-dsv4pro-rl_0.5F1/global_step_250/actor/huggingface/processor_config.json b/old_template_backup/precise_coder/4b-SFT-dsv4pro-rl_0.5F1/global_step_250/actor/huggingface/processor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..33818c7f9e991ad735fd240209f4fa73e6c28c50 --- /dev/null +++ b/old_template_backup/precise_coder/4b-SFT-dsv4pro-rl_0.5F1/global_step_250/actor/huggingface/processor_config.json @@ -0,0 +1,60 @@ +{ + "image_processor": { + "do_convert_rgb": true, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_processor_type": "Qwen2VLImageProcessor", + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "merge_size": 2, + "patch_size": 16, + "resample": 3, + "rescale_factor": 0.00392156862745098, + "size": { + "longest_edge": 16777216, + "shortest_edge": 65536 + }, + "temporal_patch_size": 2 + }, + "processor_class": "Qwen3VLProcessor", + "video_processor": { + "do_convert_rgb": true, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "do_sample_frames": true, + "fps": 2, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "max_frames": 768, + "merge_size": 2, + "min_frames": 4, + "patch_size": 16, + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_metadata": false, + "size": { + "longest_edge": 25165824, + "shortest_edge": 4096 + }, + "temporal_patch_size": 2, + "video_processor_type": "Qwen3VLVideoProcessor" + } +} diff --git a/old_template_backup/precise_coder/4b-SFT-dsv4pro-rl_0.5F1/global_step_250/actor/huggingface/tokenizer.json b/old_template_backup/precise_coder/4b-SFT-dsv4pro-rl_0.5F1/global_step_250/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad --- /dev/null +++ b/old_template_backup/precise_coder/4b-SFT-dsv4pro-rl_0.5F1/global_step_250/actor/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 +size 19989325 diff --git a/old_template_backup/precise_coder/4b-SFT-dsv4pro-rl_0.5F1/global_step_250/actor/huggingface/tokenizer_config.json b/old_template_backup/precise_coder/4b-SFT-dsv4pro-rl_0.5F1/global_step_250/actor/huggingface/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1d134cd298be1e3be25db393d93a1cefe80e3214 --- /dev/null +++ b/old_template_backup/precise_coder/4b-SFT-dsv4pro-rl_0.5F1/global_step_250/actor/huggingface/tokenizer_config.json @@ -0,0 +1,33 @@ +{ + "add_prefix_space": false, + "audio_bos_token": "<|audio_start|>", + "audio_eos_token": "<|audio_end|>", + "audio_token": "<|audio_pad|>", + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "image_token": "<|image_pad|>", + "is_local": true, + "local_files_only": false, + "model_max_length": 262144, + "model_specific_special_tokens": { + "audio_bos_token": "<|audio_start|>", + "audio_eos_token": "<|audio_end|>", + "audio_token": "<|audio_pad|>", + "image_token": "<|image_pad|>", + "video_token": "<|video_pad|>", + "vision_bos_token": "<|vision_start|>", + "vision_eos_token": "<|vision_end|>" + }, + "pad_token": "<|endoftext|>", + "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+", + "processor_class": "Qwen3VLProcessor", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null, + "video_token": "<|video_pad|>", + "vision_bos_token": "<|vision_start|>", + "vision_eos_token": "<|vision_end|>" +} diff --git a/old_template_backup/precise_coder/qwen35-4b-GRPO_U/global_step_200/actor/huggingface/config.json b/old_template_backup/precise_coder/qwen35-4b-GRPO_U/global_step_200/actor/huggingface/config.json new file mode 100644 index 0000000000000000000000000000000000000000..a50c6c903b4ceb94eb74663bc79d91145c64000b --- /dev/null +++ b/old_template_backup/precise_coder/qwen35-4b-GRPO_U/global_step_200/actor/huggingface/config.json @@ -0,0 +1,112 @@ +{ + "architectures": [ + "Qwen3_5ForConditionalGeneration" + ], + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 248046, + "image_token_id": 248056, + "model_type": "qwen3_5", + "pad_token_id": 248044, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "attn_output_gate": true, + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 248044, + "full_attention_interval": 4, + "head_dim": 256, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9216, + "layer_types": [ + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention" + ], + "linear_conv_kernel_dim": 4, + "linear_key_head_dim": 128, + "linear_num_key_heads": 16, + "linear_num_value_heads": 32, + "linear_value_head_dim": 128, + "mamba_ssm_dtype": "float32", + "max_position_embeddings": 262144, + "mlp_only_layers": [], + "model_type": "qwen3_5_text", + "mtp_num_hidden_layers": 1, + "mtp_use_dedicated_embeddings": false, + "num_attention_heads": 16, + "num_hidden_layers": 32, + "num_key_value_heads": 4, + "pad_token_id": null, + "partial_rotary_factor": 0.25, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "mrope_interleaved": true, + "mrope_section": [ + 11, + 11, + 10 + ], + "partial_rotary_factor": 0.25, + "rope_theta": 10000000, + "rope_type": "default" + }, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 248320 + }, + "tie_word_embeddings": true, + "transformers_version": "5.7.0", + "video_token_id": 248057, + "vision_config": { + "deepstack_visual_indexes": [], + "depth": 24, + "dtype": "bfloat16", + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1024, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 4096, + "model_type": "qwen3_5_vision", + "num_heads": 16, + "num_position_embeddings": 2304, + "out_hidden_size": 2560, + "patch_size": 16, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + }, + "vision_end_token_id": 248054, + "vision_start_token_id": 248053 +} diff --git a/old_template_backup/precise_coder/qwen35-9b-GRPO_U/global_step_250/actor/fsdp_config.json b/old_template_backup/precise_coder/qwen35-9b-GRPO_U/global_step_250/actor/fsdp_config.json new file mode 100644 index 0000000000000000000000000000000000000000..17ff55630675ec23d6a1d79ec7a480aa25faa5de --- /dev/null +++ b/old_template_backup/precise_coder/qwen35-9b-GRPO_U/global_step_250/actor/fsdp_config.json @@ -0,0 +1,4 @@ +{ + "FSDP_version": 2, + "world_size": 4 +} \ No newline at end of file diff --git a/old_template_backup/precise_coder/qwen35-9b-GRPO_U/global_step_250/actor/huggingface/chat_template.jinja b/old_template_backup/precise_coder/qwen35-9b-GRPO_U/global_step_250/actor/huggingface/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..a585dec894e63da457d9440ec6aa7caa16d20860 --- /dev/null +++ b/old_template_backup/precise_coder/qwen35-9b-GRPO_U/global_step_250/actor/huggingface/chat_template.jinja @@ -0,0 +1,154 @@ +{%- set image_count = namespace(value=0) %} +{%- set video_count = namespace(value=0) %} +{%- macro render_content(content, do_vision_count, is_system_content=false) %} + {%- if content is string %} + {{- content }} + {%- elif content is iterable and content is not mapping %} + {%- for item in content %} + {%- if 'image' in item or 'image_url' in item or item.type == 'image' %} + {%- if is_system_content %} + {{- raise_exception('System message cannot contain images.') }} + {%- endif %} + {%- if do_vision_count %} + {%- set image_count.value = image_count.value + 1 %} + {%- endif %} + {%- if add_vision_id %} + {{- 'Picture ' ~ image_count.value ~ ': ' }} + {%- endif %} + {{- '<|vision_start|><|image_pad|><|vision_end|>' }} + {%- elif 'video' in item or item.type == 'video' %} + {%- if is_system_content %} + {{- raise_exception('System message cannot contain videos.') }} + {%- endif %} + {%- if do_vision_count %} + {%- set video_count.value = video_count.value + 1 %} + {%- endif %} + {%- if add_vision_id %} + {{- 'Video ' ~ video_count.value ~ ': ' }} + {%- endif %} + {{- '<|vision_start|><|video_pad|><|vision_end|>' }} + {%- elif 'text' in item %} + {{- item.text }} + {%- else %} + {{- raise_exception('Unexpected item type in content.') }} + {%- endif %} + {%- endfor %} + {%- elif content is none or content is undefined %} + {{- '' }} + {%- else %} + {{- raise_exception('Unexpected content type.') }} + {%- endif %} +{%- endmacro %} +{%- if not messages %} + {{- raise_exception('No messages provided.') }} +{%- endif %} +{%- if tools and tools is iterable and tools is not mapping %} + {{- '<|im_start|>system\n' }} + {{- "# Tools\n\nYou have access to the following functions:\n\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n" }} + {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n\n\n\nvalue_1\n\n\nThis is the value for the second parameter\nthat can span\nmultiple lines\n\n\n\n\n\nReminder:\n- Function calls MUST follow the specified format: an inner block must be nested within XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n' }} + {%- if messages[0].role == 'system' %} + {%- set content = render_content(messages[0].content, false, true)|trim %} + {%- if content %} + {{- '\n\n' + content }} + {%- endif %} + {%- endif %} + {{- '<|im_end|>\n' }} +{%- else %} + {%- if messages[0].role == 'system' %} + {%- set content = render_content(messages[0].content, false, true)|trim %} + {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} +{%- for message in messages[::-1] %} + {%- set index = (messages|length - 1) - loop.index0 %} + {%- if ns.multi_step_tool and message.role == "user" %} + {%- set content = render_content(message.content, false)|trim %} + {%- if not(content.startswith('') and content.endswith('')) %} + {%- set ns.multi_step_tool = false %} + {%- set ns.last_query_index = index %} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if ns.multi_step_tool %} + {{- raise_exception('No user query found in messages.') }} +{%- endif %} +{%- for message in messages %} + {%- set content = render_content(message.content, true)|trim %} + {%- if message.role == "system" %} + {%- if not loop.first %} + {{- raise_exception('System message must be at the beginning.') }} + {%- endif %} + {%- elif message.role == "user" %} + {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {%- set reasoning_content = '' %} + {%- if message.reasoning_content is string %} + {%- set reasoning_content = message.reasoning_content %} + {%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} + {%- endif %} + {%- set reasoning_content = reasoning_content|trim %} + {%- if loop.index0 > ns.last_query_index %} + {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content + '\n\n\n' + content }} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {%- if loop.first %} + {%- if content|trim %} + {{- '\n\n\n\n' }} + {%- else %} + {{- '\n\n' }} + {%- endif %} + {%- else %} + {{- '\n\n\n' }} + {%- endif %} + {%- if tool_call.arguments is defined %} + {%- for args_name, args_value in tool_call.arguments|items %} + {{- '\n' }} + {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %} + {{- args_value }} + {{- '\n\n' }} + {%- endfor %} + {%- endif %} + {{- '\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.previtem and loop.previtem.role != "tool" %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- content }} + {{- '\n' }} + {%- if not loop.last and loop.nextitem.role != "tool" %} + {{- '<|im_end|>\n' }} + {%- elif loop.last %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- else %} + {{- raise_exception('Unexpected message role.') }} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} + {%- if enable_thinking is defined and enable_thinking is false %} + {{- '\n\n\n\n' }} + {%- else %} + {{- '\n' }} + {%- endif %} +{%- endif %} \ No newline at end of file diff --git a/old_template_backup/precise_coder/qwen35-9b-GRPO_U/global_step_250/actor/huggingface/config.json b/old_template_backup/precise_coder/qwen35-9b-GRPO_U/global_step_250/actor/huggingface/config.json new file mode 100644 index 0000000000000000000000000000000000000000..9767c2df7a0eb06a928081cfe6610a684c2ba51d --- /dev/null +++ b/old_template_backup/precise_coder/qwen35-9b-GRPO_U/global_step_250/actor/huggingface/config.json @@ -0,0 +1,112 @@ +{ + "architectures": [ + "Qwen3_5ForConditionalGeneration" + ], + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 248046, + "image_token_id": 248056, + "model_type": "qwen3_5", + "pad_token_id": 248044, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "attn_output_gate": true, + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 248044, + "full_attention_interval": 4, + "head_dim": 256, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 12288, + "layer_types": [ + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention" + ], + "linear_conv_kernel_dim": 4, + "linear_key_head_dim": 128, + "linear_num_key_heads": 16, + "linear_num_value_heads": 32, + "linear_value_head_dim": 128, + "mamba_ssm_dtype": "float32", + "max_position_embeddings": 262144, + "mlp_only_layers": [], + "model_type": "qwen3_5_text", + "mtp_num_hidden_layers": 0, + "mtp_use_dedicated_embeddings": false, + "num_attention_heads": 16, + "num_hidden_layers": 32, + "num_key_value_heads": 4, + "pad_token_id": null, + "partial_rotary_factor": 0.25, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "mrope_interleaved": true, + "mrope_section": [ + 11, + 11, + 10 + ], + "partial_rotary_factor": 0.25, + "rope_theta": 10000000, + "rope_type": "default" + }, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 248320 + }, + "tie_word_embeddings": false, + "transformers_version": "5.10.2", + "video_token_id": 248057, + "vision_config": { + "deepstack_visual_indexes": [], + "depth": 27, + "dtype": "bfloat16", + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1152, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 4304, + "model_type": "qwen3_5_vision", + "num_heads": 16, + "num_position_embeddings": 2304, + "out_hidden_size": 4096, + "patch_size": 16, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + }, + "vision_end_token_id": 248054, + "vision_start_token_id": 248053 +} diff --git a/old_template_backup/precise_coder/qwen35-9b-GRPO_U/global_step_250/actor/huggingface/generation_config.json b/old_template_backup/precise_coder/qwen35-9b-GRPO_U/global_step_250/actor/huggingface/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a8f50cfe9f041954a2175966a9ef6f88480f4769 --- /dev/null +++ b/old_template_backup/precise_coder/qwen35-9b-GRPO_U/global_step_250/actor/huggingface/generation_config.json @@ -0,0 +1,9 @@ +{ + "_from_model_config": true, + "eos_token_id": 248046, + "output_attentions": false, + "output_hidden_states": false, + "pad_token_id": 248044, + "transformers_version": "5.10.2", + "use_cache": true +} diff --git a/old_template_backup/precise_coder/qwen35-9b-GRPO_U/global_step_250/actor/huggingface/processor_config.json b/old_template_backup/precise_coder/qwen35-9b-GRPO_U/global_step_250/actor/huggingface/processor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..33818c7f9e991ad735fd240209f4fa73e6c28c50 --- /dev/null +++ b/old_template_backup/precise_coder/qwen35-9b-GRPO_U/global_step_250/actor/huggingface/processor_config.json @@ -0,0 +1,60 @@ +{ + "image_processor": { + "do_convert_rgb": true, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_processor_type": "Qwen2VLImageProcessor", + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "merge_size": 2, + "patch_size": 16, + "resample": 3, + "rescale_factor": 0.00392156862745098, + "size": { + "longest_edge": 16777216, + "shortest_edge": 65536 + }, + "temporal_patch_size": 2 + }, + "processor_class": "Qwen3VLProcessor", + "video_processor": { + "do_convert_rgb": true, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "do_sample_frames": true, + "fps": 2, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "max_frames": 768, + "merge_size": 2, + "min_frames": 4, + "patch_size": 16, + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_metadata": false, + "size": { + "longest_edge": 25165824, + "shortest_edge": 4096 + }, + "temporal_patch_size": 2, + "video_processor_type": "Qwen3VLVideoProcessor" + } +} diff --git a/old_template_backup/precise_coder/qwen35-9b-GRPO_U/global_step_250/actor/huggingface/tokenizer_config.json b/old_template_backup/precise_coder/qwen35-9b-GRPO_U/global_step_250/actor/huggingface/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1d134cd298be1e3be25db393d93a1cefe80e3214 --- /dev/null +++ b/old_template_backup/precise_coder/qwen35-9b-GRPO_U/global_step_250/actor/huggingface/tokenizer_config.json @@ -0,0 +1,33 @@ +{ + "add_prefix_space": false, + "audio_bos_token": "<|audio_start|>", + "audio_eos_token": "<|audio_end|>", + "audio_token": "<|audio_pad|>", + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "image_token": "<|image_pad|>", + "is_local": true, + "local_files_only": false, + "model_max_length": 262144, + "model_specific_special_tokens": { + "audio_bos_token": "<|audio_start|>", + "audio_eos_token": "<|audio_end|>", + "audio_token": "<|audio_pad|>", + "image_token": "<|image_pad|>", + "video_token": "<|video_pad|>", + "vision_bos_token": "<|vision_start|>", + "vision_eos_token": "<|vision_end|>" + }, + "pad_token": "<|endoftext|>", + "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+", + "processor_class": "Qwen3VLProcessor", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null, + "video_token": "<|video_pad|>", + "vision_bos_token": "<|vision_start|>", + "vision_eos_token": "<|vision_end|>" +} diff --git a/old_template_backup/precise_coder/qwen35-9b-eagrpo_a0.8_b0.05/global_step_200/actor/fsdp_config.json b/old_template_backup/precise_coder/qwen35-9b-eagrpo_a0.8_b0.05/global_step_200/actor/fsdp_config.json new file mode 100644 index 0000000000000000000000000000000000000000..17ff55630675ec23d6a1d79ec7a480aa25faa5de --- /dev/null +++ b/old_template_backup/precise_coder/qwen35-9b-eagrpo_a0.8_b0.05/global_step_200/actor/fsdp_config.json @@ -0,0 +1,4 @@ +{ + "FSDP_version": 2, + "world_size": 4 +} \ No newline at end of file diff --git a/old_template_backup/precise_coder/qwen35-9b-eagrpo_a0.8_b0.05/global_step_200/actor/huggingface/chat_template.jinja b/old_template_backup/precise_coder/qwen35-9b-eagrpo_a0.8_b0.05/global_step_200/actor/huggingface/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..a585dec894e63da457d9440ec6aa7caa16d20860 --- /dev/null +++ b/old_template_backup/precise_coder/qwen35-9b-eagrpo_a0.8_b0.05/global_step_200/actor/huggingface/chat_template.jinja @@ -0,0 +1,154 @@ +{%- set image_count = namespace(value=0) %} +{%- set video_count = namespace(value=0) %} +{%- macro render_content(content, do_vision_count, is_system_content=false) %} + {%- if content is string %} + {{- content }} + {%- elif content is iterable and content is not mapping %} + {%- for item in content %} + {%- if 'image' in item or 'image_url' in item or item.type == 'image' %} + {%- if is_system_content %} + {{- raise_exception('System message cannot contain images.') }} + {%- endif %} + {%- if do_vision_count %} + {%- set image_count.value = image_count.value + 1 %} + {%- endif %} + {%- if add_vision_id %} + {{- 'Picture ' ~ image_count.value ~ ': ' }} + {%- endif %} + {{- '<|vision_start|><|image_pad|><|vision_end|>' }} + {%- elif 'video' in item or item.type == 'video' %} + {%- if is_system_content %} + {{- raise_exception('System message cannot contain videos.') }} + {%- endif %} + {%- if do_vision_count %} + {%- set video_count.value = video_count.value + 1 %} + {%- endif %} + {%- if add_vision_id %} + {{- 'Video ' ~ video_count.value ~ ': ' }} + {%- endif %} + {{- '<|vision_start|><|video_pad|><|vision_end|>' }} + {%- elif 'text' in item %} + {{- item.text }} + {%- else %} + {{- raise_exception('Unexpected item type in content.') }} + {%- endif %} + {%- endfor %} + {%- elif content is none or content is undefined %} + {{- '' }} + {%- else %} + {{- raise_exception('Unexpected content type.') }} + {%- endif %} +{%- endmacro %} +{%- if not messages %} + {{- raise_exception('No messages provided.') }} +{%- endif %} +{%- if tools and tools is iterable and tools is not mapping %} + {{- '<|im_start|>system\n' }} + {{- "# Tools\n\nYou have access to the following functions:\n\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n" }} + {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n\n\n\nvalue_1\n\n\nThis is the value for the second parameter\nthat can span\nmultiple lines\n\n\n\n\n\nReminder:\n- Function calls MUST follow the specified format: an inner block must be nested within XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n' }} + {%- if messages[0].role == 'system' %} + {%- set content = render_content(messages[0].content, false, true)|trim %} + {%- if content %} + {{- '\n\n' + content }} + {%- endif %} + {%- endif %} + {{- '<|im_end|>\n' }} +{%- else %} + {%- if messages[0].role == 'system' %} + {%- set content = render_content(messages[0].content, false, true)|trim %} + {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} +{%- for message in messages[::-1] %} + {%- set index = (messages|length - 1) - loop.index0 %} + {%- if ns.multi_step_tool and message.role == "user" %} + {%- set content = render_content(message.content, false)|trim %} + {%- if not(content.startswith('') and content.endswith('')) %} + {%- set ns.multi_step_tool = false %} + {%- set ns.last_query_index = index %} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if ns.multi_step_tool %} + {{- raise_exception('No user query found in messages.') }} +{%- endif %} +{%- for message in messages %} + {%- set content = render_content(message.content, true)|trim %} + {%- if message.role == "system" %} + {%- if not loop.first %} + {{- raise_exception('System message must be at the beginning.') }} + {%- endif %} + {%- elif message.role == "user" %} + {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {%- set reasoning_content = '' %} + {%- if message.reasoning_content is string %} + {%- set reasoning_content = message.reasoning_content %} + {%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} + {%- endif %} + {%- set reasoning_content = reasoning_content|trim %} + {%- if loop.index0 > ns.last_query_index %} + {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content + '\n\n\n' + content }} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {%- if loop.first %} + {%- if content|trim %} + {{- '\n\n\n\n' }} + {%- else %} + {{- '\n\n' }} + {%- endif %} + {%- else %} + {{- '\n\n\n' }} + {%- endif %} + {%- if tool_call.arguments is defined %} + {%- for args_name, args_value in tool_call.arguments|items %} + {{- '\n' }} + {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %} + {{- args_value }} + {{- '\n\n' }} + {%- endfor %} + {%- endif %} + {{- '\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.previtem and loop.previtem.role != "tool" %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- content }} + {{- '\n' }} + {%- if not loop.last and loop.nextitem.role != "tool" %} + {{- '<|im_end|>\n' }} + {%- elif loop.last %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- else %} + {{- raise_exception('Unexpected message role.') }} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} + {%- if enable_thinking is defined and enable_thinking is false %} + {{- '\n\n\n\n' }} + {%- else %} + {{- '\n' }} + {%- endif %} +{%- endif %} \ No newline at end of file diff --git a/old_template_backup/precise_coder/qwen35-9b-eagrpo_a0.8_b0.05/global_step_200/actor/huggingface/generation_config.json b/old_template_backup/precise_coder/qwen35-9b-eagrpo_a0.8_b0.05/global_step_200/actor/huggingface/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a8f50cfe9f041954a2175966a9ef6f88480f4769 --- /dev/null +++ b/old_template_backup/precise_coder/qwen35-9b-eagrpo_a0.8_b0.05/global_step_200/actor/huggingface/generation_config.json @@ -0,0 +1,9 @@ +{ + "_from_model_config": true, + "eos_token_id": 248046, + "output_attentions": false, + "output_hidden_states": false, + "pad_token_id": 248044, + "transformers_version": "5.10.2", + "use_cache": true +} diff --git a/old_template_backup/precise_coder/qwen35-9b-eagrpo_a0.8_b0.05/global_step_200/actor/huggingface/tokenizer.json b/old_template_backup/precise_coder/qwen35-9b-eagrpo_a0.8_b0.05/global_step_200/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad --- /dev/null +++ b/old_template_backup/precise_coder/qwen35-9b-eagrpo_a0.8_b0.05/global_step_200/actor/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 +size 19989325 diff --git a/old_template_backup/precise_coder/qwen35-9b-eagrpo_a0.8_b0.05/global_step_200/actor/huggingface/tokenizer_config.json b/old_template_backup/precise_coder/qwen35-9b-eagrpo_a0.8_b0.05/global_step_200/actor/huggingface/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1d134cd298be1e3be25db393d93a1cefe80e3214 --- /dev/null +++ b/old_template_backup/precise_coder/qwen35-9b-eagrpo_a0.8_b0.05/global_step_200/actor/huggingface/tokenizer_config.json @@ -0,0 +1,33 @@ +{ + "add_prefix_space": false, + "audio_bos_token": "<|audio_start|>", + "audio_eos_token": "<|audio_end|>", + "audio_token": "<|audio_pad|>", + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "image_token": "<|image_pad|>", + "is_local": true, + "local_files_only": false, + "model_max_length": 262144, + "model_specific_special_tokens": { + "audio_bos_token": "<|audio_start|>", + "audio_eos_token": "<|audio_end|>", + "audio_token": "<|audio_pad|>", + "image_token": "<|image_pad|>", + "video_token": "<|video_pad|>", + "vision_bos_token": "<|vision_start|>", + "vision_eos_token": "<|vision_end|>" + }, + "pad_token": "<|endoftext|>", + "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+", + "processor_class": "Qwen3VLProcessor", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null, + "video_token": "<|video_pad|>", + "vision_bos_token": "<|vision_start|>", + "vision_eos_token": "<|vision_end|>" +} diff --git a/old_template_backup/precise_coder/qwen35-9b-rl-strreplace/global_step_350/actor/extra_state_world_size_4_rank_3.pt b/old_template_backup/precise_coder/qwen35-9b-rl-strreplace/global_step_350/actor/extra_state_world_size_4_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..b28210e8520b1ecc2709d754b5bcad92719f462f --- /dev/null +++ b/old_template_backup/precise_coder/qwen35-9b-rl-strreplace/global_step_350/actor/extra_state_world_size_4_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b57da452240ec6bfc3c620e666efe280053c4f4d6e35cc30d803558245ed6dfd +size 14973 diff --git a/old_template_backup/precise_coder/qwen35-9b-rl-strreplace/global_step_350/actor/fsdp_config.json b/old_template_backup/precise_coder/qwen35-9b-rl-strreplace/global_step_350/actor/fsdp_config.json new file mode 100644 index 0000000000000000000000000000000000000000..17ff55630675ec23d6a1d79ec7a480aa25faa5de --- /dev/null +++ b/old_template_backup/precise_coder/qwen35-9b-rl-strreplace/global_step_350/actor/fsdp_config.json @@ -0,0 +1,4 @@ +{ + "FSDP_version": 2, + "world_size": 4 +} \ No newline at end of file diff --git a/old_template_backup/precise_coder/qwen35-9b-rl-strreplace/global_step_350/actor/huggingface/chat_template.jinja b/old_template_backup/precise_coder/qwen35-9b-rl-strreplace/global_step_350/actor/huggingface/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..a585dec894e63da457d9440ec6aa7caa16d20860 --- /dev/null +++ b/old_template_backup/precise_coder/qwen35-9b-rl-strreplace/global_step_350/actor/huggingface/chat_template.jinja @@ -0,0 +1,154 @@ +{%- set image_count = namespace(value=0) %} +{%- set video_count = namespace(value=0) %} +{%- macro render_content(content, do_vision_count, is_system_content=false) %} + {%- if content is string %} + {{- content }} + {%- elif content is iterable and content is not mapping %} + {%- for item in content %} + {%- if 'image' in item or 'image_url' in item or item.type == 'image' %} + {%- if is_system_content %} + {{- raise_exception('System message cannot contain images.') }} + {%- endif %} + {%- if do_vision_count %} + {%- set image_count.value = image_count.value + 1 %} + {%- endif %} + {%- if add_vision_id %} + {{- 'Picture ' ~ image_count.value ~ ': ' }} + {%- endif %} + {{- '<|vision_start|><|image_pad|><|vision_end|>' }} + {%- elif 'video' in item or item.type == 'video' %} + {%- if is_system_content %} + {{- raise_exception('System message cannot contain videos.') }} + {%- endif %} + {%- if do_vision_count %} + {%- set video_count.value = video_count.value + 1 %} + {%- endif %} + {%- if add_vision_id %} + {{- 'Video ' ~ video_count.value ~ ': ' }} + {%- endif %} + {{- '<|vision_start|><|video_pad|><|vision_end|>' }} + {%- elif 'text' in item %} + {{- item.text }} + {%- else %} + {{- raise_exception('Unexpected item type in content.') }} + {%- endif %} + {%- endfor %} + {%- elif content is none or content is undefined %} + {{- '' }} + {%- else %} + {{- raise_exception('Unexpected content type.') }} + {%- endif %} +{%- endmacro %} +{%- if not messages %} + {{- raise_exception('No messages provided.') }} +{%- endif %} +{%- if tools and tools is iterable and tools is not mapping %} + {{- '<|im_start|>system\n' }} + {{- "# Tools\n\nYou have access to the following functions:\n\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n" }} + {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n\n\n\nvalue_1\n\n\nThis is the value for the second parameter\nthat can span\nmultiple lines\n\n\n\n\n\nReminder:\n- Function calls MUST follow the specified format: an inner block must be nested within XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n' }} + {%- if messages[0].role == 'system' %} + {%- set content = render_content(messages[0].content, false, true)|trim %} + {%- if content %} + {{- '\n\n' + content }} + {%- endif %} + {%- endif %} + {{- '<|im_end|>\n' }} +{%- else %} + {%- if messages[0].role == 'system' %} + {%- set content = render_content(messages[0].content, false, true)|trim %} + {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} +{%- for message in messages[::-1] %} + {%- set index = (messages|length - 1) - loop.index0 %} + {%- if ns.multi_step_tool and message.role == "user" %} + {%- set content = render_content(message.content, false)|trim %} + {%- if not(content.startswith('') and content.endswith('')) %} + {%- set ns.multi_step_tool = false %} + {%- set ns.last_query_index = index %} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if ns.multi_step_tool %} + {{- raise_exception('No user query found in messages.') }} +{%- endif %} +{%- for message in messages %} + {%- set content = render_content(message.content, true)|trim %} + {%- if message.role == "system" %} + {%- if not loop.first %} + {{- raise_exception('System message must be at the beginning.') }} + {%- endif %} + {%- elif message.role == "user" %} + {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {%- set reasoning_content = '' %} + {%- if message.reasoning_content is string %} + {%- set reasoning_content = message.reasoning_content %} + {%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} + {%- endif %} + {%- set reasoning_content = reasoning_content|trim %} + {%- if loop.index0 > ns.last_query_index %} + {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content + '\n\n\n' + content }} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {%- if loop.first %} + {%- if content|trim %} + {{- '\n\n\n\n' }} + {%- else %} + {{- '\n\n' }} + {%- endif %} + {%- else %} + {{- '\n\n\n' }} + {%- endif %} + {%- if tool_call.arguments is defined %} + {%- for args_name, args_value in tool_call.arguments|items %} + {{- '\n' }} + {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %} + {{- args_value }} + {{- '\n\n' }} + {%- endfor %} + {%- endif %} + {{- '\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.previtem and loop.previtem.role != "tool" %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- content }} + {{- '\n' }} + {%- if not loop.last and loop.nextitem.role != "tool" %} + {{- '<|im_end|>\n' }} + {%- elif loop.last %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- else %} + {{- raise_exception('Unexpected message role.') }} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} + {%- if enable_thinking is defined and enable_thinking is false %} + {{- '\n\n\n\n' }} + {%- else %} + {{- '\n' }} + {%- endif %} +{%- endif %} \ No newline at end of file diff --git a/old_template_backup/precise_coder/qwen35-9b-rl-strreplace/global_step_350/actor/huggingface/config.json b/old_template_backup/precise_coder/qwen35-9b-rl-strreplace/global_step_350/actor/huggingface/config.json new file mode 100644 index 0000000000000000000000000000000000000000..9767c2df7a0eb06a928081cfe6610a684c2ba51d --- /dev/null +++ b/old_template_backup/precise_coder/qwen35-9b-rl-strreplace/global_step_350/actor/huggingface/config.json @@ -0,0 +1,112 @@ +{ + "architectures": [ + "Qwen3_5ForConditionalGeneration" + ], + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 248046, + "image_token_id": 248056, + "model_type": "qwen3_5", + "pad_token_id": 248044, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "attn_output_gate": true, + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 248044, + "full_attention_interval": 4, + "head_dim": 256, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 12288, + "layer_types": [ + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention" + ], + "linear_conv_kernel_dim": 4, + "linear_key_head_dim": 128, + "linear_num_key_heads": 16, + "linear_num_value_heads": 32, + "linear_value_head_dim": 128, + "mamba_ssm_dtype": "float32", + "max_position_embeddings": 262144, + "mlp_only_layers": [], + "model_type": "qwen3_5_text", + "mtp_num_hidden_layers": 0, + "mtp_use_dedicated_embeddings": false, + "num_attention_heads": 16, + "num_hidden_layers": 32, + "num_key_value_heads": 4, + "pad_token_id": null, + "partial_rotary_factor": 0.25, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "mrope_interleaved": true, + "mrope_section": [ + 11, + 11, + 10 + ], + "partial_rotary_factor": 0.25, + "rope_theta": 10000000, + "rope_type": "default" + }, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 248320 + }, + "tie_word_embeddings": false, + "transformers_version": "5.10.2", + "video_token_id": 248057, + "vision_config": { + "deepstack_visual_indexes": [], + "depth": 27, + "dtype": "bfloat16", + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1152, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 4304, + "model_type": "qwen3_5_vision", + "num_heads": 16, + "num_position_embeddings": 2304, + "out_hidden_size": 4096, + "patch_size": 16, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + }, + "vision_end_token_id": 248054, + "vision_start_token_id": 248053 +} diff --git a/old_template_backup/precise_coder/qwen35-9b-rl-strreplace/global_step_350/actor/huggingface/generation_config.json b/old_template_backup/precise_coder/qwen35-9b-rl-strreplace/global_step_350/actor/huggingface/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a8f50cfe9f041954a2175966a9ef6f88480f4769 --- /dev/null +++ b/old_template_backup/precise_coder/qwen35-9b-rl-strreplace/global_step_350/actor/huggingface/generation_config.json @@ -0,0 +1,9 @@ +{ + "_from_model_config": true, + "eos_token_id": 248046, + "output_attentions": false, + "output_hidden_states": false, + "pad_token_id": 248044, + "transformers_version": "5.10.2", + "use_cache": true +} diff --git a/old_template_backup/precise_coder/qwen35-9b-rl-strreplace/global_step_350/actor/huggingface/tokenizer.json b/old_template_backup/precise_coder/qwen35-9b-rl-strreplace/global_step_350/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad --- /dev/null +++ b/old_template_backup/precise_coder/qwen35-9b-rl-strreplace/global_step_350/actor/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 +size 19989325 diff --git a/old_template_backup/precise_coder/qwen36-27b-GRPO_0.5F1/global_step_328/actor/fsdp_config.json b/old_template_backup/precise_coder/qwen36-27b-GRPO_0.5F1/global_step_328/actor/fsdp_config.json new file mode 100644 index 0000000000000000000000000000000000000000..c9e6473ebd621651903246ea18917c65fd53c90b --- /dev/null +++ b/old_template_backup/precise_coder/qwen36-27b-GRPO_0.5F1/global_step_328/actor/fsdp_config.json @@ -0,0 +1,4 @@ +{ + "FSDP_version": 2, + "world_size": 8 +} \ No newline at end of file diff --git a/old_template_backup/precise_coder/qwen36-27b-GRPO_0.5F1/global_step_328/actor/huggingface/config.json b/old_template_backup/precise_coder/qwen36-27b-GRPO_0.5F1/global_step_328/actor/huggingface/config.json new file mode 100644 index 0000000000000000000000000000000000000000..3d12eb85194cfb1bef8634ea037c1e37103fd806 --- /dev/null +++ b/old_template_backup/precise_coder/qwen36-27b-GRPO_0.5F1/global_step_328/actor/huggingface/config.json @@ -0,0 +1,145 @@ +{ + "architectures": [ + "Qwen3_5ForConditionalGeneration" + ], + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 248046, + "image_token_id": 248056, + "language_model_only": false, + "model_type": "qwen3_5", + "pad_token_id": 248044, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "attn_output_gate": true, + "bos_token_id": 248044, + "dtype": "bfloat16", + "eos_token_id": 248044, + "full_attention_interval": 4, + "head_dim": 256, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 17408, + "layer_types": [ + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention" + ], + "linear_conv_kernel_dim": 4, + "linear_key_head_dim": 128, + "linear_num_key_heads": 16, + "linear_num_value_heads": 48, + "linear_value_head_dim": 128, + "mamba_ssm_dtype": "float32", + "max_position_embeddings": 262144, + "model_type": "qwen3_5_text", + "mtp_num_hidden_layers": 0, + "mtp_use_dedicated_embeddings": false, + "num_attention_heads": 24, + "num_hidden_layers": 64, + "num_key_value_heads": 4, + "output_gate_type": "swish", + "pad_token_id": null, + "partial_rotary_factor": 0.25, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "mrope_interleaved": true, + "mrope_section": [ + 11, + 11, + 10 + ], + "partial_rotary_factor": 0.25, + "rope_theta": 10000000, + "rope_type": "default" + }, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 248320 + }, + "tie_word_embeddings": false, + "transformers_version": "5.10.2", + "video_token_id": 248057, + "vision_config": { + "deepstack_visual_indexes": [], + "depth": 27, + "dtype": "bfloat16", + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1152, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 4304, + "model_type": "qwen3_5_vision", + "num_heads": 16, + "num_position_embeddings": 2304, + "out_hidden_size": 5120, + "patch_size": 16, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + }, + "vision_end_token_id": 248054, + "vision_start_token_id": 248053 +} diff --git a/old_template_backup/precise_coder/qwen36-27b-GRPO_0.5F1/global_step_328/actor/huggingface/generation_config.json b/old_template_backup/precise_coder/qwen36-27b-GRPO_0.5F1/global_step_328/actor/huggingface/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..bfbe4ce905a96d5dd4daec54ce29ca2b7213de64 --- /dev/null +++ b/old_template_backup/precise_coder/qwen36-27b-GRPO_0.5F1/global_step_328/actor/huggingface/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 248044, + "do_sample": true, + "eos_token_id": [ + 248046, + 248044 + ], + "pad_token_id": 248044, + "temperature": 1.0, + "top_k": 20, + "top_p": 0.95, + "transformers_version": "5.10.2" +} diff --git a/old_template_backup/precise_coder/qwen36-27b-GRPO_0.5F1/global_step_328/actor/huggingface/model.safetensors.index.json b/old_template_backup/precise_coder/qwen36-27b-GRPO_0.5F1/global_step_328/actor/huggingface/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..c9a8209bf1d2178d36d88f52e663b84b91d77fb5 --- /dev/null +++ b/old_template_backup/precise_coder/qwen36-27b-GRPO_0.5F1/global_step_328/actor/huggingface/model.safetensors.index.json @@ -0,0 +1,1192 @@ +{ + "metadata": { + "total_parameters": 27356728560, + "total_size": 54713457120 + }, + "weight_map": { + "lm_head.weight": "model-00001-of-00002.safetensors", + "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.linear_attn.A_log": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.linear_attn.norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.linear_attn.A_log": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.linear_attn.norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.linear_attn.norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.linear_attn.norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.linear_attn.A_log": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.36.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.36.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.36.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.36.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.36.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.36.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.36.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.36.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.36.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.36.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.36.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.36.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.36.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.36.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.37.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.37.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.37.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.37.linear_attn.dt_bias": "model-00002-of-00002.safetensors", + "model.language_model.layers.37.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.37.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.37.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.37.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.37.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.37.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.37.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.37.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.37.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.37.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.38.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.38.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.38.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.38.linear_attn.dt_bias": "model-00002-of-00002.safetensors", + "model.language_model.layers.38.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.38.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.38.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.38.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.38.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.38.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.38.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.38.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.38.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.38.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.39.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.39.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.39.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.39.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.39.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.39.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.39.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.39.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.39.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.39.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.39.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.40.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.40.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.40.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.40.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.40.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.40.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.40.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.40.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.40.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.40.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.40.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.40.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.40.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.40.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.41.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.41.linear_attn.A_log": "model-00002-of-00002.safetensors", + "model.language_model.layers.41.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.41.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.41.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.41.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.41.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.41.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.41.linear_attn.norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.41.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.41.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.41.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.41.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.41.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.42.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.42.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.42.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.42.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.42.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.42.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.42.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.42.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.42.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.42.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.42.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.42.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.42.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.42.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.43.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.43.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.43.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.43.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.43.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.43.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.43.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.43.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.43.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.43.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.43.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.44.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.44.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.44.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.44.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.44.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.44.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.44.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.44.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.44.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.44.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.44.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.44.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.44.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.44.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.45.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.45.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.45.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.45.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.45.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.45.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.45.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.45.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.45.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.45.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.45.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.45.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.45.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.45.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.46.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.46.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.46.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.46.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.46.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.46.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.46.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.46.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.46.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.46.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.46.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.46.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.46.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.46.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.47.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.47.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.47.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.47.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.47.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.47.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.47.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.47.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.47.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.47.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.47.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.48.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.48.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.48.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.48.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.48.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.48.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.48.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.48.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.48.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.48.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.48.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.48.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.48.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.48.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.49.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.49.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.49.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.49.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.49.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.49.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.49.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.49.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.49.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.49.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.49.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.49.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.49.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.49.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.50.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.50.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.50.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.50.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.50.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.50.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.50.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.50.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.50.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.50.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.50.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.50.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.50.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.50.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.51.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.51.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.51.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.51.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.51.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.51.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.51.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.51.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.51.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.51.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.51.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.52.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.52.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.52.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.52.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.52.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.52.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.52.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.52.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.52.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.52.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.52.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.52.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.52.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.52.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.53.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.53.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.53.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.53.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.53.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.53.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.53.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.53.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.53.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.53.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.53.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.53.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.53.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.53.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.54.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.54.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.54.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.54.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.54.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.54.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.54.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.54.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.54.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.54.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.54.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.54.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.54.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.54.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.55.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.55.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.55.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.55.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.55.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.55.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.55.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.55.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.55.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.55.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.55.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.56.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.56.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.56.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.56.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.56.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.56.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.56.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.56.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.56.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.56.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.56.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.56.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.56.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.56.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.57.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.57.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.57.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.57.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.57.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.57.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.57.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.57.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.57.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.57.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.57.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.57.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.57.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.57.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.58.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.58.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.58.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.58.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.58.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.58.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.58.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.58.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.58.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.58.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.58.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.58.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.58.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.58.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.59.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.59.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.59.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.59.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.59.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.59.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.59.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.59.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.59.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.59.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.59.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.linear_attn.dt_bias": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.60.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.60.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.60.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.60.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.60.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.60.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.60.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.60.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.60.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.60.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.60.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.60.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.60.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.60.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.61.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.61.linear_attn.A_log": "model-00002-of-00002.safetensors", + "model.language_model.layers.61.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.61.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.61.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.61.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.61.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.61.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.61.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.61.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.61.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.61.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.61.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.61.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.62.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.62.linear_attn.A_log": "model-00002-of-00002.safetensors", + "model.language_model.layers.62.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.62.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.62.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.62.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.62.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.62.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.62.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.62.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.62.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.62.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.62.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.62.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.63.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.63.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.63.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.63.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.63.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.63.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.63.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.63.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.63.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.63.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.63.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.linear_attn.A_log": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.linear_attn.A_log": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.linear_attn.dt_bias": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.linear_attn.norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.24.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.24.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.24.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.24.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.24.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.24.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.25.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.25.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.25.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.25.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.25.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.25.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.25.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.25.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.25.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.26.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.26.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.26.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.26.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.26.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.26.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.26.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.26.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.merger.norm.bias": "model-00001-of-00002.safetensors", + "model.visual.merger.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.pos_embed.weight": "model-00001-of-00002.safetensors" + } +} diff --git a/old_template_backup/precise_coder/qwen36-27b-GRPO_0.5F1/global_step_328/actor/huggingface/processor_config.json b/old_template_backup/precise_coder/qwen36-27b-GRPO_0.5F1/global_step_328/actor/huggingface/processor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..33818c7f9e991ad735fd240209f4fa73e6c28c50 --- /dev/null +++ b/old_template_backup/precise_coder/qwen36-27b-GRPO_0.5F1/global_step_328/actor/huggingface/processor_config.json @@ -0,0 +1,60 @@ +{ + "image_processor": { + "do_convert_rgb": true, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_processor_type": "Qwen2VLImageProcessor", + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "merge_size": 2, + "patch_size": 16, + "resample": 3, + "rescale_factor": 0.00392156862745098, + "size": { + "longest_edge": 16777216, + "shortest_edge": 65536 + }, + "temporal_patch_size": 2 + }, + "processor_class": "Qwen3VLProcessor", + "video_processor": { + "do_convert_rgb": true, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "do_sample_frames": true, + "fps": 2, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "max_frames": 768, + "merge_size": 2, + "min_frames": 4, + "patch_size": 16, + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_metadata": false, + "size": { + "longest_edge": 25165824, + "shortest_edge": 4096 + }, + "temporal_patch_size": 2, + "video_processor_type": "Qwen3VLVideoProcessor" + } +} diff --git a/old_template_backup/precise_coder/qwen36-27b-GRPO_0.5F1/global_step_328/actor/huggingface/tokenizer_config.json b/old_template_backup/precise_coder/qwen36-27b-GRPO_0.5F1/global_step_328/actor/huggingface/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1d134cd298be1e3be25db393d93a1cefe80e3214 --- /dev/null +++ b/old_template_backup/precise_coder/qwen36-27b-GRPO_0.5F1/global_step_328/actor/huggingface/tokenizer_config.json @@ -0,0 +1,33 @@ +{ + "add_prefix_space": false, + "audio_bos_token": "<|audio_start|>", + "audio_eos_token": "<|audio_end|>", + "audio_token": "<|audio_pad|>", + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "image_token": "<|image_pad|>", + "is_local": true, + "local_files_only": false, + "model_max_length": 262144, + "model_specific_special_tokens": { + "audio_bos_token": "<|audio_start|>", + "audio_eos_token": "<|audio_end|>", + "audio_token": "<|audio_pad|>", + "image_token": "<|image_pad|>", + "video_token": "<|video_pad|>", + "vision_bos_token": "<|vision_start|>", + "vision_eos_token": "<|vision_end|>" + }, + "pad_token": "<|endoftext|>", + "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+", + "processor_class": "Qwen3VLProcessor", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null, + "video_token": "<|video_pad|>", + "vision_bos_token": "<|vision_start|>", + "vision_eos_token": "<|vision_end|>" +} diff --git a/precise_coder/4b_rl_k0.17/best_ckpt_state.json b/precise_coder/4b_rl_k0.17/best_ckpt_state.json new file mode 100644 index 0000000000000000000000000000000000000000..2f29de27316a1cc2b2782d2654a4e71ec856678b --- /dev/null +++ b/precise_coder/4b_rl_k0.17/best_ckpt_state.json @@ -0,0 +1 @@ +{"best_val_score": 1.1833594109164969, "best_global_step": 325, "no_improve_rounds": 1} \ No newline at end of file diff --git a/precise_coder/4b_rl_k0.33_f1ur/best_ckpt_state.json b/precise_coder/4b_rl_k0.33_f1ur/best_ckpt_state.json new file mode 100644 index 0000000000000000000000000000000000000000..5a66d59e3a7f39c1f69a79db074613c19ecfe4b8 --- /dev/null +++ b/precise_coder/4b_rl_k0.33_f1ur/best_ckpt_state.json @@ -0,0 +1 @@ +{"best_val_score": 1.1673349282709558, "best_global_step": 328, "no_improve_rounds": 0} \ No newline at end of file diff --git a/precise_coder/4b_rl_k0.33_gated_v2/best_ckpt_state.json b/precise_coder/4b_rl_k0.33_gated_v2/best_ckpt_state.json new file mode 100644 index 0000000000000000000000000000000000000000..e5e8f8e78beac465647385970f877514a51ee183 --- /dev/null +++ b/precise_coder/4b_rl_k0.33_gated_v2/best_ckpt_state.json @@ -0,0 +1 @@ +{"best_val_score": 1.1875389739711852, "best_global_step": 275, "no_improve_rounds": 3} \ No newline at end of file diff --git a/precise_coder/4b_rl_k0.33_gated_v2/latest_checkpointed_iteration.txt b/precise_coder/4b_rl_k0.33_gated_v2/latest_checkpointed_iteration.txt new file mode 100644 index 0000000000000000000000000000000000000000..41a4a819ada66b2e8f7fea82f094eb1314f2e9ca --- /dev/null +++ b/precise_coder/4b_rl_k0.33_gated_v2/latest_checkpointed_iteration.txt @@ -0,0 +1 @@ +328 \ No newline at end of file diff --git a/precise_coder/4b_rl_k0.5_run2/latest_checkpointed_iteration.txt b/precise_coder/4b_rl_k0.5_run2/latest_checkpointed_iteration.txt new file mode 100644 index 0000000000000000000000000000000000000000..41a4a819ada66b2e8f7fea82f094eb1314f2e9ca --- /dev/null +++ b/precise_coder/4b_rl_k0.5_run2/latest_checkpointed_iteration.txt @@ -0,0 +1 @@ +328 \ No newline at end of file diff --git a/precise_coder/4b_rl_k0.67/latest_checkpointed_iteration.txt b/precise_coder/4b_rl_k0.67/latest_checkpointed_iteration.txt new file mode 100644 index 0000000000000000000000000000000000000000..41a4a819ada66b2e8f7fea82f094eb1314f2e9ca --- /dev/null +++ b/precise_coder/4b_rl_k0.67/latest_checkpointed_iteration.txt @@ -0,0 +1 @@ +328 \ No newline at end of file diff --git a/precise_coder/4b_rl_k1.0/latest_checkpointed_iteration.txt b/precise_coder/4b_rl_k1.0/latest_checkpointed_iteration.txt new file mode 100644 index 0000000000000000000000000000000000000000..41a4a819ada66b2e8f7fea82f094eb1314f2e9ca --- /dev/null +++ b/precise_coder/4b_rl_k1.0/latest_checkpointed_iteration.txt @@ -0,0 +1 @@ +328 \ No newline at end of file diff --git a/precise_coder_sft/4b-SFT-27b-1ep/global_step_45/data_1.pt b/precise_coder_sft/4b-SFT-27b-1ep/global_step_45/data_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..76bf6f34efb7914871003792c4abb36936ff4060 --- /dev/null +++ b/precise_coder_sft/4b-SFT-27b-1ep/global_step_45/data_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01d388198af6652ac4828c7179c92625d98cf0bf7233619da0d1af68525d9cb3 +size 1959 diff --git a/precise_coder_sft/4b-SFT-27b-1ep/global_step_45/huggingface/config.json b/precise_coder_sft/4b-SFT-27b-1ep/global_step_45/huggingface/config.json new file mode 100644 index 0000000000000000000000000000000000000000..0e8cd2d6f8b5c82e83b6479da2639aa4f7f24473 --- /dev/null +++ b/precise_coder_sft/4b-SFT-27b-1ep/global_step_45/huggingface/config.json @@ -0,0 +1,112 @@ +{ + "architectures": [ + "Qwen3_5ForConditionalGeneration" + ], + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 248046, + "image_token_id": 248056, + "model_type": "qwen3_5", + "pad_token_id": 248044, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "attn_output_gate": true, + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 248044, + "full_attention_interval": 4, + "head_dim": 256, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9216, + "layer_types": [ + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention" + ], + "linear_conv_kernel_dim": 4, + "linear_key_head_dim": 128, + "linear_num_key_heads": 16, + "linear_num_value_heads": 32, + "linear_value_head_dim": 128, + "mamba_ssm_dtype": "float32", + "max_position_embeddings": 262144, + "mlp_only_layers": [], + "model_type": "qwen3_5_text", + "mtp_num_hidden_layers": 0, + "mtp_use_dedicated_embeddings": false, + "num_attention_heads": 16, + "num_hidden_layers": 32, + "num_key_value_heads": 4, + "pad_token_id": null, + "partial_rotary_factor": 0.25, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "mrope_interleaved": true, + "mrope_section": [ + 11, + 11, + 10 + ], + "partial_rotary_factor": 0.25, + "rope_theta": 10000000, + "rope_type": "default" + }, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 248320 + }, + "tie_word_embeddings": true, + "transformers_version": "5.10.2", + "video_token_id": 248057, + "vision_config": { + "deepstack_visual_indexes": [], + "depth": 24, + "dtype": "bfloat16", + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1024, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 4096, + "model_type": "qwen3_5_vision", + "num_heads": 16, + "num_position_embeddings": 2304, + "out_hidden_size": 2560, + "patch_size": 16, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + }, + "vision_end_token_id": 248054, + "vision_start_token_id": 248053 +} diff --git a/precise_coder_sft/4b-SFT-27b-1ep/global_step_45/huggingface/processor_config.json b/precise_coder_sft/4b-SFT-27b-1ep/global_step_45/huggingface/processor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..33818c7f9e991ad735fd240209f4fa73e6c28c50 --- /dev/null +++ b/precise_coder_sft/4b-SFT-27b-1ep/global_step_45/huggingface/processor_config.json @@ -0,0 +1,60 @@ +{ + "image_processor": { + "do_convert_rgb": true, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_processor_type": "Qwen2VLImageProcessor", + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "merge_size": 2, + "patch_size": 16, + "resample": 3, + "rescale_factor": 0.00392156862745098, + "size": { + "longest_edge": 16777216, + "shortest_edge": 65536 + }, + "temporal_patch_size": 2 + }, + "processor_class": "Qwen3VLProcessor", + "video_processor": { + "do_convert_rgb": true, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "do_sample_frames": true, + "fps": 2, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "max_frames": 768, + "merge_size": 2, + "min_frames": 4, + "patch_size": 16, + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_metadata": false, + "size": { + "longest_edge": 25165824, + "shortest_edge": 4096 + }, + "temporal_patch_size": 2, + "video_processor_type": "Qwen3VLVideoProcessor" + } +} diff --git a/precise_coder_sft/4b-SFT-27b-hard-2ep/global_step_22/data_0.pt b/precise_coder_sft/4b-SFT-27b-hard-2ep/global_step_22/data_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..42d1c6c1aa8839797cae93d81e022d658869c3df --- /dev/null +++ b/precise_coder_sft/4b-SFT-27b-hard-2ep/global_step_22/data_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66e6cbf56078cf8489a89c479446e9270abcbc9250269897529ce8ada0970b41 +size 1959 diff --git a/precise_coder_sft/4b-SFT-27b-hard-2ep/global_step_22/fsdp_config.json b/precise_coder_sft/4b-SFT-27b-hard-2ep/global_step_22/fsdp_config.json new file mode 100644 index 0000000000000000000000000000000000000000..174466767b39126350641a0bf123be05f6c491b0 --- /dev/null +++ b/precise_coder_sft/4b-SFT-27b-hard-2ep/global_step_22/fsdp_config.json @@ -0,0 +1,4 @@ +{ + "FSDP_version": 2, + "world_size": 2 +} \ No newline at end of file diff --git a/precise_coder_sft/4b-SFT-27b-hard-2ep/global_step_22/huggingface/config.json b/precise_coder_sft/4b-SFT-27b-hard-2ep/global_step_22/huggingface/config.json new file mode 100644 index 0000000000000000000000000000000000000000..0e8cd2d6f8b5c82e83b6479da2639aa4f7f24473 --- /dev/null +++ b/precise_coder_sft/4b-SFT-27b-hard-2ep/global_step_22/huggingface/config.json @@ -0,0 +1,112 @@ +{ + "architectures": [ + "Qwen3_5ForConditionalGeneration" + ], + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 248046, + "image_token_id": 248056, + "model_type": "qwen3_5", + "pad_token_id": 248044, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "attn_output_gate": true, + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 248044, + "full_attention_interval": 4, + "head_dim": 256, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9216, + "layer_types": [ + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention" + ], + "linear_conv_kernel_dim": 4, + "linear_key_head_dim": 128, + "linear_num_key_heads": 16, + "linear_num_value_heads": 32, + "linear_value_head_dim": 128, + "mamba_ssm_dtype": "float32", + "max_position_embeddings": 262144, + "mlp_only_layers": [], + "model_type": "qwen3_5_text", + "mtp_num_hidden_layers": 0, + "mtp_use_dedicated_embeddings": false, + "num_attention_heads": 16, + "num_hidden_layers": 32, + "num_key_value_heads": 4, + "pad_token_id": null, + "partial_rotary_factor": 0.25, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "mrope_interleaved": true, + "mrope_section": [ + 11, + 11, + 10 + ], + "partial_rotary_factor": 0.25, + "rope_theta": 10000000, + "rope_type": "default" + }, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 248320 + }, + "tie_word_embeddings": true, + "transformers_version": "5.10.2", + "video_token_id": 248057, + "vision_config": { + "deepstack_visual_indexes": [], + "depth": 24, + "dtype": "bfloat16", + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1024, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 4096, + "model_type": "qwen3_5_vision", + "num_heads": 16, + "num_position_embeddings": 2304, + "out_hidden_size": 2560, + "patch_size": 16, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + }, + "vision_end_token_id": 248054, + "vision_start_token_id": 248053 +} diff --git a/precise_coder_sft/4b-SFT-27b-hard-2ep/global_step_22/huggingface/generation_config.json b/precise_coder_sft/4b-SFT-27b-hard-2ep/global_step_22/huggingface/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a8f50cfe9f041954a2175966a9ef6f88480f4769 --- /dev/null +++ b/precise_coder_sft/4b-SFT-27b-hard-2ep/global_step_22/huggingface/generation_config.json @@ -0,0 +1,9 @@ +{ + "_from_model_config": true, + "eos_token_id": 248046, + "output_attentions": false, + "output_hidden_states": false, + "pad_token_id": 248044, + "transformers_version": "5.10.2", + "use_cache": true +} diff --git a/precise_coder_sft/4b-SFT-dsv4pro-1ep/global_step_41/data_0.pt b/precise_coder_sft/4b-SFT-dsv4pro-1ep/global_step_41/data_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..ec5e8474745f208c273e05f9854862b5bc32f0e2 --- /dev/null +++ b/precise_coder_sft/4b-SFT-dsv4pro-1ep/global_step_41/data_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad22b632726f4c2e7304cca05175489f9bded8fdb9c9e685ce5ae214d851cfc4 +size 1959 diff --git a/precise_coder_sft/4b-SFT-dsv4pro-1ep/global_step_41/data_1.pt b/precise_coder_sft/4b-SFT-dsv4pro-1ep/global_step_41/data_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..c7c34f792e322f8d4dad3ac87cd29fa235c8464a --- /dev/null +++ b/precise_coder_sft/4b-SFT-dsv4pro-1ep/global_step_41/data_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5277972669b2bdf79747d5073be6bbba98cc51541832f647399b23adbc6a0e75 +size 1959 diff --git a/precise_coder_sft/4b-SFT-dsv4pro-1ep/global_step_41/huggingface/processor_config.json b/precise_coder_sft/4b-SFT-dsv4pro-1ep/global_step_41/huggingface/processor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..33818c7f9e991ad735fd240209f4fa73e6c28c50 --- /dev/null +++ b/precise_coder_sft/4b-SFT-dsv4pro-1ep/global_step_41/huggingface/processor_config.json @@ -0,0 +1,60 @@ +{ + "image_processor": { + "do_convert_rgb": true, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_processor_type": "Qwen2VLImageProcessor", + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "merge_size": 2, + "patch_size": 16, + "resample": 3, + "rescale_factor": 0.00392156862745098, + "size": { + "longest_edge": 16777216, + "shortest_edge": 65536 + }, + "temporal_patch_size": 2 + }, + "processor_class": "Qwen3VLProcessor", + "video_processor": { + "do_convert_rgb": true, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "do_sample_frames": true, + "fps": 2, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "max_frames": 768, + "merge_size": 2, + "min_frames": 4, + "patch_size": 16, + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_metadata": false, + "size": { + "longest_edge": 25165824, + "shortest_edge": 4096 + }, + "temporal_patch_size": 2, + "video_processor_type": "Qwen3VLVideoProcessor" + } +} diff --git a/precise_coder_sft/4b-SFT-dsv4pro-hard-2ep/global_step_21/data_0.pt b/precise_coder_sft/4b-SFT-dsv4pro-hard-2ep/global_step_21/data_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..a13654a03f4a1113405e072cfc29195be6f6d087 --- /dev/null +++ b/precise_coder_sft/4b-SFT-dsv4pro-hard-2ep/global_step_21/data_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1e4acb9eee8f5f86f7d5ecbf0ca3161ad881ba755418df11d6bff5100745f2c +size 1959 diff --git a/precise_coder_sft/4b-SFT-dsv4pro-hard-2ep/global_step_21/data_1.pt b/precise_coder_sft/4b-SFT-dsv4pro-hard-2ep/global_step_21/data_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..d86a891e230a180c66ec04aeebecd9387b0cfea5 --- /dev/null +++ b/precise_coder_sft/4b-SFT-dsv4pro-hard-2ep/global_step_21/data_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1582fd7cad47d38326c702756a2574876313a48f0bed0b41ee53eae89e6459b3 +size 1959 diff --git a/precise_coder_sft/4b-SFT-dsv4pro-hard-2ep/global_step_21/huggingface/chat_template.jinja b/precise_coder_sft/4b-SFT-dsv4pro-hard-2ep/global_step_21/huggingface/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..a585dec894e63da457d9440ec6aa7caa16d20860 --- /dev/null +++ b/precise_coder_sft/4b-SFT-dsv4pro-hard-2ep/global_step_21/huggingface/chat_template.jinja @@ -0,0 +1,154 @@ +{%- set image_count = namespace(value=0) %} +{%- set video_count = namespace(value=0) %} +{%- macro render_content(content, do_vision_count, is_system_content=false) %} + {%- if content is string %} + {{- content }} + {%- elif content is iterable and content is not mapping %} + {%- for item in content %} + {%- if 'image' in item or 'image_url' in item or item.type == 'image' %} + {%- if is_system_content %} + {{- raise_exception('System message cannot contain images.') }} + {%- endif %} + {%- if do_vision_count %} + {%- set image_count.value = image_count.value + 1 %} + {%- endif %} + {%- if add_vision_id %} + {{- 'Picture ' ~ image_count.value ~ ': ' }} + {%- endif %} + {{- '<|vision_start|><|image_pad|><|vision_end|>' }} + {%- elif 'video' in item or item.type == 'video' %} + {%- if is_system_content %} + {{- raise_exception('System message cannot contain videos.') }} + {%- endif %} + {%- if do_vision_count %} + {%- set video_count.value = video_count.value + 1 %} + {%- endif %} + {%- if add_vision_id %} + {{- 'Video ' ~ video_count.value ~ ': ' }} + {%- endif %} + {{- '<|vision_start|><|video_pad|><|vision_end|>' }} + {%- elif 'text' in item %} + {{- item.text }} + {%- else %} + {{- raise_exception('Unexpected item type in content.') }} + {%- endif %} + {%- endfor %} + {%- elif content is none or content is undefined %} + {{- '' }} + {%- else %} + {{- raise_exception('Unexpected content type.') }} + {%- endif %} +{%- endmacro %} +{%- if not messages %} + {{- raise_exception('No messages provided.') }} +{%- endif %} +{%- if tools and tools is iterable and tools is not mapping %} + {{- '<|im_start|>system\n' }} + {{- "# Tools\n\nYou have access to the following functions:\n\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n" }} + {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n\n\n\nvalue_1\n\n\nThis is the value for the second parameter\nthat can span\nmultiple lines\n\n\n\n\n\nReminder:\n- Function calls MUST follow the specified format: an inner block must be nested within XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n' }} + {%- if messages[0].role == 'system' %} + {%- set content = render_content(messages[0].content, false, true)|trim %} + {%- if content %} + {{- '\n\n' + content }} + {%- endif %} + {%- endif %} + {{- '<|im_end|>\n' }} +{%- else %} + {%- if messages[0].role == 'system' %} + {%- set content = render_content(messages[0].content, false, true)|trim %} + {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} +{%- for message in messages[::-1] %} + {%- set index = (messages|length - 1) - loop.index0 %} + {%- if ns.multi_step_tool and message.role == "user" %} + {%- set content = render_content(message.content, false)|trim %} + {%- if not(content.startswith('') and content.endswith('')) %} + {%- set ns.multi_step_tool = false %} + {%- set ns.last_query_index = index %} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if ns.multi_step_tool %} + {{- raise_exception('No user query found in messages.') }} +{%- endif %} +{%- for message in messages %} + {%- set content = render_content(message.content, true)|trim %} + {%- if message.role == "system" %} + {%- if not loop.first %} + {{- raise_exception('System message must be at the beginning.') }} + {%- endif %} + {%- elif message.role == "user" %} + {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {%- set reasoning_content = '' %} + {%- if message.reasoning_content is string %} + {%- set reasoning_content = message.reasoning_content %} + {%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} + {%- endif %} + {%- set reasoning_content = reasoning_content|trim %} + {%- if loop.index0 > ns.last_query_index %} + {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content + '\n\n\n' + content }} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {%- if loop.first %} + {%- if content|trim %} + {{- '\n\n\n\n' }} + {%- else %} + {{- '\n\n' }} + {%- endif %} + {%- else %} + {{- '\n\n\n' }} + {%- endif %} + {%- if tool_call.arguments is defined %} + {%- for args_name, args_value in tool_call.arguments|items %} + {{- '\n' }} + {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %} + {{- args_value }} + {{- '\n\n' }} + {%- endfor %} + {%- endif %} + {{- '\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.previtem and loop.previtem.role != "tool" %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- content }} + {{- '\n' }} + {%- if not loop.last and loop.nextitem.role != "tool" %} + {{- '<|im_end|>\n' }} + {%- elif loop.last %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- else %} + {{- raise_exception('Unexpected message role.') }} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} + {%- if enable_thinking is defined and enable_thinking is false %} + {{- '\n\n\n\n' }} + {%- else %} + {{- '\n' }} + {%- endif %} +{%- endif %} \ No newline at end of file diff --git a/precise_coder_sft/4b-SFT-dsv4pro-hard-2ep/global_step_21/huggingface/config.json b/precise_coder_sft/4b-SFT-dsv4pro-hard-2ep/global_step_21/huggingface/config.json new file mode 100644 index 0000000000000000000000000000000000000000..0e8cd2d6f8b5c82e83b6479da2639aa4f7f24473 --- /dev/null +++ b/precise_coder_sft/4b-SFT-dsv4pro-hard-2ep/global_step_21/huggingface/config.json @@ -0,0 +1,112 @@ +{ + "architectures": [ + "Qwen3_5ForConditionalGeneration" + ], + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 248046, + "image_token_id": 248056, + "model_type": "qwen3_5", + "pad_token_id": 248044, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "attn_output_gate": true, + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 248044, + "full_attention_interval": 4, + "head_dim": 256, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9216, + "layer_types": [ + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention" + ], + "linear_conv_kernel_dim": 4, + "linear_key_head_dim": 128, + "linear_num_key_heads": 16, + "linear_num_value_heads": 32, + "linear_value_head_dim": 128, + "mamba_ssm_dtype": "float32", + "max_position_embeddings": 262144, + "mlp_only_layers": [], + "model_type": "qwen3_5_text", + "mtp_num_hidden_layers": 0, + "mtp_use_dedicated_embeddings": false, + "num_attention_heads": 16, + "num_hidden_layers": 32, + "num_key_value_heads": 4, + "pad_token_id": null, + "partial_rotary_factor": 0.25, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "mrope_interleaved": true, + "mrope_section": [ + 11, + 11, + 10 + ], + "partial_rotary_factor": 0.25, + "rope_theta": 10000000, + "rope_type": "default" + }, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 248320 + }, + "tie_word_embeddings": true, + "transformers_version": "5.10.2", + "video_token_id": 248057, + "vision_config": { + "deepstack_visual_indexes": [], + "depth": 24, + "dtype": "bfloat16", + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1024, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 4096, + "model_type": "qwen3_5_vision", + "num_heads": 16, + "num_position_embeddings": 2304, + "out_hidden_size": 2560, + "patch_size": 16, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + }, + "vision_end_token_id": 248054, + "vision_start_token_id": 248053 +} diff --git a/precise_coder_sft/4b-SFT-dsv4pro-hard-2ep/global_step_21/huggingface/processor_config.json b/precise_coder_sft/4b-SFT-dsv4pro-hard-2ep/global_step_21/huggingface/processor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..33818c7f9e991ad735fd240209f4fa73e6c28c50 --- /dev/null +++ b/precise_coder_sft/4b-SFT-dsv4pro-hard-2ep/global_step_21/huggingface/processor_config.json @@ -0,0 +1,60 @@ +{ + "image_processor": { + "do_convert_rgb": true, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_processor_type": "Qwen2VLImageProcessor", + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "merge_size": 2, + "patch_size": 16, + "resample": 3, + "rescale_factor": 0.00392156862745098, + "size": { + "longest_edge": 16777216, + "shortest_edge": 65536 + }, + "temporal_patch_size": 2 + }, + "processor_class": "Qwen3VLProcessor", + "video_processor": { + "do_convert_rgb": true, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "do_sample_frames": true, + "fps": 2, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "max_frames": 768, + "merge_size": 2, + "min_frames": 4, + "patch_size": 16, + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_metadata": false, + "size": { + "longest_edge": 25165824, + "shortest_edge": 4096 + }, + "temporal_patch_size": 2, + "video_processor_type": "Qwen3VLVideoProcessor" + } +} diff --git a/precise_coder_sft/4b-SFT-glm-1ep/global_step_31/data_0.pt b/precise_coder_sft/4b-SFT-glm-1ep/global_step_31/data_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..461c568889b068324d9b89e326c27a3bc1c067e2 --- /dev/null +++ b/precise_coder_sft/4b-SFT-glm-1ep/global_step_31/data_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bc91d06c5062de4fa4b55b5e9aabcdb923a5d22f8add893072a4fafa0e269c9 +size 1959 diff --git a/precise_coder_sft/4b-SFT-glm-1ep/global_step_31/fsdp_config.json b/precise_coder_sft/4b-SFT-glm-1ep/global_step_31/fsdp_config.json new file mode 100644 index 0000000000000000000000000000000000000000..174466767b39126350641a0bf123be05f6c491b0 --- /dev/null +++ b/precise_coder_sft/4b-SFT-glm-1ep/global_step_31/fsdp_config.json @@ -0,0 +1,4 @@ +{ + "FSDP_version": 2, + "world_size": 2 +} \ No newline at end of file diff --git a/precise_coder_sft/4b-SFT-glm-1ep/global_step_31/huggingface/config.json b/precise_coder_sft/4b-SFT-glm-1ep/global_step_31/huggingface/config.json new file mode 100644 index 0000000000000000000000000000000000000000..0e8cd2d6f8b5c82e83b6479da2639aa4f7f24473 --- /dev/null +++ b/precise_coder_sft/4b-SFT-glm-1ep/global_step_31/huggingface/config.json @@ -0,0 +1,112 @@ +{ + "architectures": [ + "Qwen3_5ForConditionalGeneration" + ], + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 248046, + "image_token_id": 248056, + "model_type": "qwen3_5", + "pad_token_id": 248044, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "attn_output_gate": true, + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 248044, + "full_attention_interval": 4, + "head_dim": 256, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9216, + "layer_types": [ + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention" + ], + "linear_conv_kernel_dim": 4, + "linear_key_head_dim": 128, + "linear_num_key_heads": 16, + "linear_num_value_heads": 32, + "linear_value_head_dim": 128, + "mamba_ssm_dtype": "float32", + "max_position_embeddings": 262144, + "mlp_only_layers": [], + "model_type": "qwen3_5_text", + "mtp_num_hidden_layers": 0, + "mtp_use_dedicated_embeddings": false, + "num_attention_heads": 16, + "num_hidden_layers": 32, + "num_key_value_heads": 4, + "pad_token_id": null, + "partial_rotary_factor": 0.25, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "mrope_interleaved": true, + "mrope_section": [ + 11, + 11, + 10 + ], + "partial_rotary_factor": 0.25, + "rope_theta": 10000000, + "rope_type": "default" + }, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 248320 + }, + "tie_word_embeddings": true, + "transformers_version": "5.10.2", + "video_token_id": 248057, + "vision_config": { + "deepstack_visual_indexes": [], + "depth": 24, + "dtype": "bfloat16", + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1024, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 4096, + "model_type": "qwen3_5_vision", + "num_heads": 16, + "num_position_embeddings": 2304, + "out_hidden_size": 2560, + "patch_size": 16, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + }, + "vision_end_token_id": 248054, + "vision_start_token_id": 248053 +} diff --git a/precise_coder_sft/4b-SFT-glm-1ep/global_step_31/huggingface/generation_config.json b/precise_coder_sft/4b-SFT-glm-1ep/global_step_31/huggingface/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a8f50cfe9f041954a2175966a9ef6f88480f4769 --- /dev/null +++ b/precise_coder_sft/4b-SFT-glm-1ep/global_step_31/huggingface/generation_config.json @@ -0,0 +1,9 @@ +{ + "_from_model_config": true, + "eos_token_id": 248046, + "output_attentions": false, + "output_hidden_states": false, + "pad_token_id": 248044, + "transformers_version": "5.10.2", + "use_cache": true +} diff --git a/precise_coder_sft/4b-SFT-glm-1ep/global_step_31/huggingface/tokenizer_config.json b/precise_coder_sft/4b-SFT-glm-1ep/global_step_31/huggingface/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1d134cd298be1e3be25db393d93a1cefe80e3214 --- /dev/null +++ b/precise_coder_sft/4b-SFT-glm-1ep/global_step_31/huggingface/tokenizer_config.json @@ -0,0 +1,33 @@ +{ + "add_prefix_space": false, + "audio_bos_token": "<|audio_start|>", + "audio_eos_token": "<|audio_end|>", + "audio_token": "<|audio_pad|>", + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "image_token": "<|image_pad|>", + "is_local": true, + "local_files_only": false, + "model_max_length": 262144, + "model_specific_special_tokens": { + "audio_bos_token": "<|audio_start|>", + "audio_eos_token": "<|audio_end|>", + "audio_token": "<|audio_pad|>", + "image_token": "<|image_pad|>", + "video_token": "<|video_pad|>", + "vision_bos_token": "<|vision_start|>", + "vision_eos_token": "<|vision_end|>" + }, + "pad_token": "<|endoftext|>", + "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+", + "processor_class": "Qwen3VLProcessor", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null, + "video_token": "<|video_pad|>", + "vision_bos_token": "<|vision_start|>", + "vision_eos_token": "<|vision_end|>" +} diff --git a/precise_coder_sft/4b-SFT-glm-hard-2ep/global_step_21/data_0.pt b/precise_coder_sft/4b-SFT-glm-hard-2ep/global_step_21/data_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..52710e1036b8285e5fb27f46f3f51239d8032fd6 --- /dev/null +++ b/precise_coder_sft/4b-SFT-glm-hard-2ep/global_step_21/data_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62e3bb5c3bbd99dd65fc0eee36e191758cf15efeb21842515ceb2afb6272de1d +size 1959 diff --git a/precise_coder_sft/4b-SFT-glm-hard-2ep/global_step_21/huggingface/processor_config.json b/precise_coder_sft/4b-SFT-glm-hard-2ep/global_step_21/huggingface/processor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..33818c7f9e991ad735fd240209f4fa73e6c28c50 --- /dev/null +++ b/precise_coder_sft/4b-SFT-glm-hard-2ep/global_step_21/huggingface/processor_config.json @@ -0,0 +1,60 @@ +{ + "image_processor": { + "do_convert_rgb": true, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_processor_type": "Qwen2VLImageProcessor", + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "merge_size": 2, + "patch_size": 16, + "resample": 3, + "rescale_factor": 0.00392156862745098, + "size": { + "longest_edge": 16777216, + "shortest_edge": 65536 + }, + "temporal_patch_size": 2 + }, + "processor_class": "Qwen3VLProcessor", + "video_processor": { + "do_convert_rgb": true, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "do_sample_frames": true, + "fps": 2, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "max_frames": 768, + "merge_size": 2, + "min_frames": 4, + "patch_size": 16, + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_metadata": false, + "size": { + "longest_edge": 25165824, + "shortest_edge": 4096 + }, + "temporal_patch_size": 2, + "video_processor_type": "Qwen3VLVideoProcessor" + } +} diff --git a/precise_coder_sft/4b-SFT-rej32-think7k/global_step_29/data_0.pt b/precise_coder_sft/4b-SFT-rej32-think7k/global_step_29/data_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..d976b1d0b2f76be03057f63a3debdf03b292077a --- /dev/null +++ b/precise_coder_sft/4b-SFT-rej32-think7k/global_step_29/data_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4af67613a4b8800eb734deab79baa52d9f07149e70acf9f50f19ea9919600d48 +size 1959 diff --git a/precise_coder_sft/4b-SFT-rej32-think7k/global_step_29/fsdp_config.json b/precise_coder_sft/4b-SFT-rej32-think7k/global_step_29/fsdp_config.json new file mode 100644 index 0000000000000000000000000000000000000000..174466767b39126350641a0bf123be05f6c491b0 --- /dev/null +++ b/precise_coder_sft/4b-SFT-rej32-think7k/global_step_29/fsdp_config.json @@ -0,0 +1,4 @@ +{ + "FSDP_version": 2, + "world_size": 2 +} \ No newline at end of file diff --git a/precise_coder_sft/4b-SFT-rej32-think7k/global_step_29/huggingface/processor_config.json b/precise_coder_sft/4b-SFT-rej32-think7k/global_step_29/huggingface/processor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..33818c7f9e991ad735fd240209f4fa73e6c28c50 --- /dev/null +++ b/precise_coder_sft/4b-SFT-rej32-think7k/global_step_29/huggingface/processor_config.json @@ -0,0 +1,60 @@ +{ + "image_processor": { + "do_convert_rgb": true, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_processor_type": "Qwen2VLImageProcessor", + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "merge_size": 2, + "patch_size": 16, + "resample": 3, + "rescale_factor": 0.00392156862745098, + "size": { + "longest_edge": 16777216, + "shortest_edge": 65536 + }, + "temporal_patch_size": 2 + }, + "processor_class": "Qwen3VLProcessor", + "video_processor": { + "do_convert_rgb": true, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "do_sample_frames": true, + "fps": 2, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "max_frames": 768, + "merge_size": 2, + "min_frames": 4, + "patch_size": 16, + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_metadata": false, + "size": { + "longest_edge": 25165824, + "shortest_edge": 4096 + }, + "temporal_patch_size": 2, + "video_processor_type": "Qwen3VLVideoProcessor" + } +} diff --git a/precise_coder_sft/4b-SFT-rej32-think7k/global_step_29/huggingface/tokenizer_config.json b/precise_coder_sft/4b-SFT-rej32-think7k/global_step_29/huggingface/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1d134cd298be1e3be25db393d93a1cefe80e3214 --- /dev/null +++ b/precise_coder_sft/4b-SFT-rej32-think7k/global_step_29/huggingface/tokenizer_config.json @@ -0,0 +1,33 @@ +{ + "add_prefix_space": false, + "audio_bos_token": "<|audio_start|>", + "audio_eos_token": "<|audio_end|>", + "audio_token": "<|audio_pad|>", + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "image_token": "<|image_pad|>", + "is_local": true, + "local_files_only": false, + "model_max_length": 262144, + "model_specific_special_tokens": { + "audio_bos_token": "<|audio_start|>", + "audio_eos_token": "<|audio_end|>", + "audio_token": "<|audio_pad|>", + "image_token": "<|image_pad|>", + "video_token": "<|video_pad|>", + "vision_bos_token": "<|vision_start|>", + "vision_eos_token": "<|vision_end|>" + }, + "pad_token": "<|endoftext|>", + "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+", + "processor_class": "Qwen3VLProcessor", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null, + "video_token": "<|video_pad|>", + "vision_bos_token": "<|vision_start|>", + "vision_eos_token": "<|vision_end|>" +} diff --git a/precise_coder_sft/4b-SFT-rej32-trackA/global_step_28/huggingface/generation_config.json b/precise_coder_sft/4b-SFT-rej32-trackA/global_step_28/huggingface/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a8f50cfe9f041954a2175966a9ef6f88480f4769 --- /dev/null +++ b/precise_coder_sft/4b-SFT-rej32-trackA/global_step_28/huggingface/generation_config.json @@ -0,0 +1,9 @@ +{ + "_from_model_config": true, + "eos_token_id": 248046, + "output_attentions": false, + "output_hidden_states": false, + "pad_token_id": 248044, + "transformers_version": "5.10.2", + "use_cache": true +} diff --git a/precise_coder_sft/4b-SFT-rej32-trackA/global_step_28/huggingface/processor_config.json b/precise_coder_sft/4b-SFT-rej32-trackA/global_step_28/huggingface/processor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..33818c7f9e991ad735fd240209f4fa73e6c28c50 --- /dev/null +++ b/precise_coder_sft/4b-SFT-rej32-trackA/global_step_28/huggingface/processor_config.json @@ -0,0 +1,60 @@ +{ + "image_processor": { + "do_convert_rgb": true, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_processor_type": "Qwen2VLImageProcessor", + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "merge_size": 2, + "patch_size": 16, + "resample": 3, + "rescale_factor": 0.00392156862745098, + "size": { + "longest_edge": 16777216, + "shortest_edge": 65536 + }, + "temporal_patch_size": 2 + }, + "processor_class": "Qwen3VLProcessor", + "video_processor": { + "do_convert_rgb": true, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "do_sample_frames": true, + "fps": 2, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "max_frames": 768, + "merge_size": 2, + "min_frames": 4, + "patch_size": 16, + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_metadata": false, + "size": { + "longest_edge": 25165824, + "shortest_edge": 4096 + }, + "temporal_patch_size": 2, + "video_processor_type": "Qwen3VLVideoProcessor" + } +} diff --git a/precise_coder_sft/4b-SFT-rej32-trackA/latest_checkpointed_iteration.txt b/precise_coder_sft/4b-SFT-rej32-trackA/latest_checkpointed_iteration.txt new file mode 100644 index 0000000000000000000000000000000000000000..9902f17848a8974ab57d57999b74a63198fe6e23 --- /dev/null +++ b/precise_coder_sft/4b-SFT-rej32-trackA/latest_checkpointed_iteration.txt @@ -0,0 +1 @@ +28 diff --git a/precise_coder_sft/4b-SFT-rej32-trackB/global_step_39/huggingface/config.json b/precise_coder_sft/4b-SFT-rej32-trackB/global_step_39/huggingface/config.json new file mode 100644 index 0000000000000000000000000000000000000000..0e8cd2d6f8b5c82e83b6479da2639aa4f7f24473 --- /dev/null +++ b/precise_coder_sft/4b-SFT-rej32-trackB/global_step_39/huggingface/config.json @@ -0,0 +1,112 @@ +{ + "architectures": [ + "Qwen3_5ForConditionalGeneration" + ], + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 248046, + "image_token_id": 248056, + "model_type": "qwen3_5", + "pad_token_id": 248044, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "attn_output_gate": true, + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 248044, + "full_attention_interval": 4, + "head_dim": 256, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9216, + "layer_types": [ + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention" + ], + "linear_conv_kernel_dim": 4, + "linear_key_head_dim": 128, + "linear_num_key_heads": 16, + "linear_num_value_heads": 32, + "linear_value_head_dim": 128, + "mamba_ssm_dtype": "float32", + "max_position_embeddings": 262144, + "mlp_only_layers": [], + "model_type": "qwen3_5_text", + "mtp_num_hidden_layers": 0, + "mtp_use_dedicated_embeddings": false, + "num_attention_heads": 16, + "num_hidden_layers": 32, + "num_key_value_heads": 4, + "pad_token_id": null, + "partial_rotary_factor": 0.25, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "mrope_interleaved": true, + "mrope_section": [ + 11, + 11, + 10 + ], + "partial_rotary_factor": 0.25, + "rope_theta": 10000000, + "rope_type": "default" + }, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 248320 + }, + "tie_word_embeddings": true, + "transformers_version": "5.10.2", + "video_token_id": 248057, + "vision_config": { + "deepstack_visual_indexes": [], + "depth": 24, + "dtype": "bfloat16", + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1024, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 4096, + "model_type": "qwen3_5_vision", + "num_heads": 16, + "num_position_embeddings": 2304, + "out_hidden_size": 2560, + "patch_size": 16, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + }, + "vision_end_token_id": 248054, + "vision_start_token_id": 248053 +} diff --git a/precise_coder_sft/4b-SFT-rej32-trackB/global_step_39/huggingface/tokenizer_config.json b/precise_coder_sft/4b-SFT-rej32-trackB/global_step_39/huggingface/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1d134cd298be1e3be25db393d93a1cefe80e3214 --- /dev/null +++ b/precise_coder_sft/4b-SFT-rej32-trackB/global_step_39/huggingface/tokenizer_config.json @@ -0,0 +1,33 @@ +{ + "add_prefix_space": false, + "audio_bos_token": "<|audio_start|>", + "audio_eos_token": "<|audio_end|>", + "audio_token": "<|audio_pad|>", + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "image_token": "<|image_pad|>", + "is_local": true, + "local_files_only": false, + "model_max_length": 262144, + "model_specific_special_tokens": { + "audio_bos_token": "<|audio_start|>", + "audio_eos_token": "<|audio_end|>", + "audio_token": "<|audio_pad|>", + "image_token": "<|image_pad|>", + "video_token": "<|video_pad|>", + "vision_bos_token": "<|vision_start|>", + "vision_eos_token": "<|vision_end|>" + }, + "pad_token": "<|endoftext|>", + "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+", + "processor_class": "Qwen3VLProcessor", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null, + "video_token": "<|video_pad|>", + "vision_bos_token": "<|vision_start|>", + "vision_eos_token": "<|vision_end|>" +} diff --git a/precise_coder_sft/4b-SFT-rej32-trackC/global_step_18/huggingface/chat_template.jinja b/precise_coder_sft/4b-SFT-rej32-trackC/global_step_18/huggingface/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..a585dec894e63da457d9440ec6aa7caa16d20860 --- /dev/null +++ b/precise_coder_sft/4b-SFT-rej32-trackC/global_step_18/huggingface/chat_template.jinja @@ -0,0 +1,154 @@ +{%- set image_count = namespace(value=0) %} +{%- set video_count = namespace(value=0) %} +{%- macro render_content(content, do_vision_count, is_system_content=false) %} + {%- if content is string %} + {{- content }} + {%- elif content is iterable and content is not mapping %} + {%- for item in content %} + {%- if 'image' in item or 'image_url' in item or item.type == 'image' %} + {%- if is_system_content %} + {{- raise_exception('System message cannot contain images.') }} + {%- endif %} + {%- if do_vision_count %} + {%- set image_count.value = image_count.value + 1 %} + {%- endif %} + {%- if add_vision_id %} + {{- 'Picture ' ~ image_count.value ~ ': ' }} + {%- endif %} + {{- '<|vision_start|><|image_pad|><|vision_end|>' }} + {%- elif 'video' in item or item.type == 'video' %} + {%- if is_system_content %} + {{- raise_exception('System message cannot contain videos.') }} + {%- endif %} + {%- if do_vision_count %} + {%- set video_count.value = video_count.value + 1 %} + {%- endif %} + {%- if add_vision_id %} + {{- 'Video ' ~ video_count.value ~ ': ' }} + {%- endif %} + {{- '<|vision_start|><|video_pad|><|vision_end|>' }} + {%- elif 'text' in item %} + {{- item.text }} + {%- else %} + {{- raise_exception('Unexpected item type in content.') }} + {%- endif %} + {%- endfor %} + {%- elif content is none or content is undefined %} + {{- '' }} + {%- else %} + {{- raise_exception('Unexpected content type.') }} + {%- endif %} +{%- endmacro %} +{%- if not messages %} + {{- raise_exception('No messages provided.') }} +{%- endif %} +{%- if tools and tools is iterable and tools is not mapping %} + {{- '<|im_start|>system\n' }} + {{- "# Tools\n\nYou have access to the following functions:\n\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n" }} + {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n\n\n\nvalue_1\n\n\nThis is the value for the second parameter\nthat can span\nmultiple lines\n\n\n\n\n\nReminder:\n- Function calls MUST follow the specified format: an inner block must be nested within XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n' }} + {%- if messages[0].role == 'system' %} + {%- set content = render_content(messages[0].content, false, true)|trim %} + {%- if content %} + {{- '\n\n' + content }} + {%- endif %} + {%- endif %} + {{- '<|im_end|>\n' }} +{%- else %} + {%- if messages[0].role == 'system' %} + {%- set content = render_content(messages[0].content, false, true)|trim %} + {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} +{%- for message in messages[::-1] %} + {%- set index = (messages|length - 1) - loop.index0 %} + {%- if ns.multi_step_tool and message.role == "user" %} + {%- set content = render_content(message.content, false)|trim %} + {%- if not(content.startswith('') and content.endswith('')) %} + {%- set ns.multi_step_tool = false %} + {%- set ns.last_query_index = index %} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if ns.multi_step_tool %} + {{- raise_exception('No user query found in messages.') }} +{%- endif %} +{%- for message in messages %} + {%- set content = render_content(message.content, true)|trim %} + {%- if message.role == "system" %} + {%- if not loop.first %} + {{- raise_exception('System message must be at the beginning.') }} + {%- endif %} + {%- elif message.role == "user" %} + {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {%- set reasoning_content = '' %} + {%- if message.reasoning_content is string %} + {%- set reasoning_content = message.reasoning_content %} + {%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} + {%- endif %} + {%- set reasoning_content = reasoning_content|trim %} + {%- if loop.index0 > ns.last_query_index %} + {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content + '\n\n\n' + content }} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {%- if loop.first %} + {%- if content|trim %} + {{- '\n\n\n\n' }} + {%- else %} + {{- '\n\n' }} + {%- endif %} + {%- else %} + {{- '\n\n\n' }} + {%- endif %} + {%- if tool_call.arguments is defined %} + {%- for args_name, args_value in tool_call.arguments|items %} + {{- '\n' }} + {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %} + {{- args_value }} + {{- '\n\n' }} + {%- endfor %} + {%- endif %} + {{- '\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.previtem and loop.previtem.role != "tool" %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- content }} + {{- '\n' }} + {%- if not loop.last and loop.nextitem.role != "tool" %} + {{- '<|im_end|>\n' }} + {%- elif loop.last %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- else %} + {{- raise_exception('Unexpected message role.') }} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} + {%- if enable_thinking is defined and enable_thinking is false %} + {{- '\n\n\n\n' }} + {%- else %} + {{- '\n' }} + {%- endif %} +{%- endif %} \ No newline at end of file diff --git a/precise_coder_sft/4b-SFT-rej32-trackC/global_step_18/huggingface/config.json b/precise_coder_sft/4b-SFT-rej32-trackC/global_step_18/huggingface/config.json new file mode 100644 index 0000000000000000000000000000000000000000..0e8cd2d6f8b5c82e83b6479da2639aa4f7f24473 --- /dev/null +++ b/precise_coder_sft/4b-SFT-rej32-trackC/global_step_18/huggingface/config.json @@ -0,0 +1,112 @@ +{ + "architectures": [ + "Qwen3_5ForConditionalGeneration" + ], + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 248046, + "image_token_id": 248056, + "model_type": "qwen3_5", + "pad_token_id": 248044, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "attn_output_gate": true, + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 248044, + "full_attention_interval": 4, + "head_dim": 256, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9216, + "layer_types": [ + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention", + "linear_attention", + "linear_attention", + "linear_attention", + "full_attention" + ], + "linear_conv_kernel_dim": 4, + "linear_key_head_dim": 128, + "linear_num_key_heads": 16, + "linear_num_value_heads": 32, + "linear_value_head_dim": 128, + "mamba_ssm_dtype": "float32", + "max_position_embeddings": 262144, + "mlp_only_layers": [], + "model_type": "qwen3_5_text", + "mtp_num_hidden_layers": 0, + "mtp_use_dedicated_embeddings": false, + "num_attention_heads": 16, + "num_hidden_layers": 32, + "num_key_value_heads": 4, + "pad_token_id": null, + "partial_rotary_factor": 0.25, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "mrope_interleaved": true, + "mrope_section": [ + 11, + 11, + 10 + ], + "partial_rotary_factor": 0.25, + "rope_theta": 10000000, + "rope_type": "default" + }, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 248320 + }, + "tie_word_embeddings": true, + "transformers_version": "5.10.2", + "video_token_id": 248057, + "vision_config": { + "deepstack_visual_indexes": [], + "depth": 24, + "dtype": "bfloat16", + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1024, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 4096, + "model_type": "qwen3_5_vision", + "num_heads": 16, + "num_position_embeddings": 2304, + "out_hidden_size": 2560, + "patch_size": 16, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + }, + "vision_end_token_id": 248054, + "vision_start_token_id": 248053 +} diff --git a/precise_coder_sft/4b-SFT-rej32-trackC/global_step_18/huggingface/generation_config.json b/precise_coder_sft/4b-SFT-rej32-trackC/global_step_18/huggingface/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a8f50cfe9f041954a2175966a9ef6f88480f4769 --- /dev/null +++ b/precise_coder_sft/4b-SFT-rej32-trackC/global_step_18/huggingface/generation_config.json @@ -0,0 +1,9 @@ +{ + "_from_model_config": true, + "eos_token_id": 248046, + "output_attentions": false, + "output_hidden_states": false, + "pad_token_id": 248044, + "transformers_version": "5.10.2", + "use_cache": true +} diff --git a/precise_coder_sft/4b-SFT-rej32-trackC/global_step_18/huggingface/tokenizer_config.json b/precise_coder_sft/4b-SFT-rej32-trackC/global_step_18/huggingface/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1d134cd298be1e3be25db393d93a1cefe80e3214 --- /dev/null +++ b/precise_coder_sft/4b-SFT-rej32-trackC/global_step_18/huggingface/tokenizer_config.json @@ -0,0 +1,33 @@ +{ + "add_prefix_space": false, + "audio_bos_token": "<|audio_start|>", + "audio_eos_token": "<|audio_end|>", + "audio_token": "<|audio_pad|>", + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "image_token": "<|image_pad|>", + "is_local": true, + "local_files_only": false, + "model_max_length": 262144, + "model_specific_special_tokens": { + "audio_bos_token": "<|audio_start|>", + "audio_eos_token": "<|audio_end|>", + "audio_token": "<|audio_pad|>", + "image_token": "<|image_pad|>", + "video_token": "<|video_pad|>", + "vision_bos_token": "<|vision_start|>", + "vision_eos_token": "<|vision_end|>" + }, + "pad_token": "<|endoftext|>", + "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+", + "processor_class": "Qwen3VLProcessor", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null, + "video_token": "<|video_pad|>", + "vision_bos_token": "<|vision_start|>", + "vision_eos_token": "<|vision_end|>" +} diff --git a/precise_coder_sft/4b-SFT-rej32/global_step_32/data_0.pt b/precise_coder_sft/4b-SFT-rej32/global_step_32/data_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..e9cb23197c67bc87e6184cf4e475b2a90c2920ad --- /dev/null +++ b/precise_coder_sft/4b-SFT-rej32/global_step_32/data_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d39b1b4820fa8c574dd8e4d052a2c7b33b14ad816c2204b558f8db11074166fe +size 1959 diff --git a/precise_coder_sft/4b-SFT-rej32/global_step_32/data_1.pt b/precise_coder_sft/4b-SFT-rej32/global_step_32/data_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..834c21e2d57c4cda2e3d1f59abf6ef0e02747906 --- /dev/null +++ b/precise_coder_sft/4b-SFT-rej32/global_step_32/data_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:271ac8b1e5c7764b87e38e254981c879e9da8bc43815a6f678e9e663c69eecd5 +size 1959