commit e1a82bb5b3b1e7133d72335cddd8d968232ceb10 Author: ModelHub XC Date: Sat Jun 13 16:08:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: groc/recursive-sat-qwen2.5-1.5b Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1763cfc --- /dev/null +++ b/.gitattributes @@ -0,0 +1,37 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +model.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..229c1c3 --- /dev/null +++ b/README.md @@ -0,0 +1,110 @@ +--- +base_model: Qwen/Qwen2.5-1.5B-Instruct +library_name: transformers +pipeline_tag: text-generation +tags: +- paper-model +- recursive-reasoning +- sat +- qwen2.5 +- transformers +datasets: +- LLM4Code/SATBench +license: mit +--- + +# recursive-sat-qwen2.5-1.5b + +This is a paper model: the `REC-3` release artifact from a paper-aligned replication of recursive SAT reasoning at 1.5B scale. + +It is a supervised fine-tune of `Qwen/Qwen2.5-1.5B-Instruct` trained on recursive SAT traces derived from SATBench with explicit `` / `` structure. The goal is research replication and analysis, not general-purpose production use. + +## What This Model Is + +- Base model: `Qwen/Qwen2.5-1.5B-Instruct` +- Release artifact: `results/runs/REC-3/published_model` +- Training run: `REC-3` +- Seed: `303` +- Config: `configs/rec_seed303.yaml` +- Dataset source: `LLM4Code/SATBench` +- Task: SAT / UNSAT classification via recursive trace supervision + +## Why REC-3 + +`REC-1` and `REC-3` tie on mean accuracy, but `REC-3` is the cleaner release candidate on end-to-end behavior: + +- Mean accuracy: `45.33%` +- Easy: `39.0%` +- Medium: `54.0%` +- Hard: `43.0%` +- Parse failure rate: `7.0%` +- Valid trace rate: `99.0%` + +Compared with `REC-1`, `REC-3` keeps the same mean accuracy while reducing parse failure (`7.0%` vs `8.33%`), improving hard accuracy (`43.0%` vs `42.0%`), and slightly improving valid trace rate (`99.0%` vs `98.33%`). + +## Important Caveat + +This is a paper model, not a claim of robust general recursive reasoning. + +The underlying paper draft treats the result as a qualified replication: + +- recursive SFT improves end-to-end SATBench accuracy over raw direct prompting +- the strongest gain is on medium-difficulty SAT instances +- absolute performance remains far below the 3B source-paper result +- recursion behavior is still shallow overall + +Use this release as a research artifact tied to the experiment, metrics, and discussion in the paper repo. + +## Training Summary + +- Objective: `recursive_sft` +- Train examples: `74,827` +- Validation examples: `619` +- Global step: `46,770` +- Best checkpoint: `checkpoint-9354` +- Accelerator used for the main run: `cuda` + +## Evaluation Summary + +Main held-out evaluation uses `100` examples each from SATBench easy, medium, and hard buckets. + +Baseline vs released model: + +- Base direct prompt mean accuracy: `37.33%` +- `REC-3` mean accuracy: `45.33%` +- Absolute gain: `+8.0 points` +- Base parse failure rate: `28.67%` +- `REC-3` parse failure rate: `7.0%` + +## Prompt Format + +The model was trained on recursive traces using: + +- ` ... ` for subproblem decomposition +- ` ... ` for compact returned answers + +It is best treated as a specialized research model for this protocolized SAT setting. + +## Files In This Release + +- `model.safetensors` +- `config.json` +- `generation_config.json` +- `tokenizer.json` +- `tokenizer_config.json` +- `chat_template.jinja` +- `export_metadata.json` + +## Intended Use + +- paper artifact release +- replication reference +- SAT recursive-trace evaluation +- qualitative inspection of recursive protocol behavior + +## Out Of Scope + +- production reasoning system +- general mathematical reasoning benchmark model +- safety-critical use +- claims beyond the SATBench replication setting \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..bdf7919 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,54 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0]['role'] == 'system' %} + {{- messages[0]['content'] }} + {%- else %} + {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }} + {%- endif %} + {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0]['role'] == 'system' %} + {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }} + {%- else %} + {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role }} + {%- if message.content %} + {{- '\n' + message.content }} + {%- endif %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {{- tool_call.arguments | tojson }} + {{- '}\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/config.json b/config.json new file mode 100644 index 0000000..ae8317b --- /dev/null +++ b/config.json @@ -0,0 +1,61 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 151645, + "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": 32768, + "max_window_layers": 21, + "model_type": "qwen2", + "num_attention_heads": 12, + "num_hidden_layers": 28, + "num_key_value_heads": 2, + "pad_token_id": 151643, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "5.3.0", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/export_metadata.json b/export_metadata.json new file mode 100644 index 0000000..9137ac7 --- /dev/null +++ b/export_metadata.json @@ -0,0 +1,13 @@ +{ + "source_checkpoint": "results/runs/REC-3/checkpoints/checkpoint-9354", + "output_dir": "results/runs/REC-3/published_model", + "copied_files": [ + "chat_template.jinja", + "config.json", + "generation_config.json", + "model.safetensors", + "tokenizer.json", + "tokenizer_config.json" + ], + "run_dir": "results/runs/REC-3" +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..7e4dad7 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,13 @@ +{ + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "repetition_penalty": 1.1, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.3.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..e7da92f --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6e056dfe59bd3cd54b7d29e88baf9a7ac784902f0339a7005bdcb68ab97fbdb +size 3087467144 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..34510ff --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8 +size 11421892 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..7d75d3b --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,29 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "is_local": false, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}