Clear old files before upload

README.md

@@ -1,7 +0,0 @@
----
-base_model:
-- deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
-license: mit
----
-
-The Math Agent of Mixture-Style MAS in the paper: Recursive Multi-Agent Systems. (base model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B)

adapter.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:412489bb426d08c1f3c8e07bafc00f83afd10e0a5522cb4cd886730c5a924461
-size 9458829

adapter_config.json

@@ -1,3 +0,0 @@
-{
-  "adapter_type": "ln_res_adapter"
-}

chat_template.jinja

@@ -1 +0,0 @@
-{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\n'}}{% endif %}

config.json

@@ -1,62 +0,0 @@
-{
-  "architectures": [
-    "Qwen2ForCausalLM"
-  ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 151643,
-  "dtype": "bfloat16",
-  "eos_token_id": 151643,
-  "hidden_act": "silu",
-  "hidden_size": 1536,
-  "initializer_range": 0.02,
-  "intermediate_size": 8960,
-  "layer_types": [
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention"
-  ],
-  "max_position_embeddings": 131072,
-  "max_window_layers": 21,
-  "model_type": "qwen2",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 28,
-  "num_key_value_heads": 2,
-  "pad_token_id": null,
-  "rms_norm_eps": 1e-06,
-  "rope_parameters": {
-    "rope_theta": 10000,
-    "rope_type": "default"
-  },
-  "sliding_window": null,
-  "tie_word_embeddings": false,
-  "transformers_version": "5.3.0",
-  "use_cache": true,
-  "use_mrope": false,
-  "use_sliding_window": false,
-  "vocab_size": 151936
-}

generation_config.json

@@ -1,9 +0,0 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 151646,
-  "do_sample": true,
-  "eos_token_id": 151643,
-  "temperature": 0.6,
-  "top_p": 0.95,
-  "transformers_version": "5.3.0"
-}

model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:16bea0a35dba47a078ac1750e001512a02837da37c70c3c806244efbe9efefc8
-size 3554214752

tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:322664cdc3082b6eba003af5228a77ca1d7936d402e584ecde8f15d3d98bdb72
-size 11421911

tokenizer_config.json

@@ -1,13 +0,0 @@
-{
-  "backend": "tokenizers",
-  "bos_token": "<｜begin▁of▁sentence｜>",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<｜end▁of▁sentence｜>",
-  "is_local": true,
-  "legacy": true,
-  "model_max_length": 16384,
-  "pad_token": "<｜end▁of▁sentence｜>",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "TokenizersBackend",
-  "unk_token": null
-}