From 2fddd402027b27c8ab9f181604137b8029615197 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Mon, 5 Oct 2026 01:09:19 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: srivarenya/MoM-python-slm-grpo Source: Original Platform --- .gitattributes | 36 ++++++++++++++++++++++++ README.md | 63 ++++++++++++++++++++++++++++++++++++++++++ chat_template.jinja | 54 ++++++++++++++++++++++++++++++++++++ config.json | 61 ++++++++++++++++++++++++++++++++++++++++ generation_config.json | 13 +++++++++ model.safetensors | 3 ++ tokenizer.json | 3 ++ tokenizer_config.json | 31 +++++++++++++++++++++ 8 files changed, 264 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 chat_template.jinja create mode 100644 config.json create mode 100644 generation_config.json create mode 100644 model.safetensors create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..835c759 --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +license: apache-2.0 +base_model: srivarenya/MoM-python-slm +pipeline_tag: text-generation +library_name: transformers +tags: [code, python, qwen2.5-coder, dora, grpo, rlvr, reinforcement-learning, mixture-of-models, code-generation] +language: [en] +--- + +# MoM-Python-SLM-GRPO (1.5B) + +The **spec-driven code-generation node** of a **Mixture-of-Models (MoM)** mesh — the GRPO/RLVR-tuned +successor to [`srivarenya/MoM-python-slm`](https://huggingface.co/srivarenya/MoM-python-slm). Given a +Python task (optionally with an upstream context packet), it returns reasoning followed by a function. +It shares the Qwen2.5-Coder tokenizer with the other generative nodes, which is what makes logit-space +fusion across the mesh valid. + +- **Warm-started from:** [`srivarenya/MoM-python-slm`](https://huggingface.co/srivarenya/MoM-python-slm) + (DoRA r=64 SFT of Qwen2.5-Coder-1.5B-Instruct) +- **Method:** GRPO (Group Relative Policy Optimization, RLVR) — a fresh DoRA r=64 adapter trained 500 + steps, then merged. +- **Reward:** `0.8 · execution + 0.1 · format + 0.1 · LLM-judge`. Execution reward runs each completion + against the problem's `assert` tests in a sandbox (binary pass/fail) — this is the load-bearing signal. + Two-sided abstention: `NEED_INPUT` is rewarded only on underspecified prompts. +- **GRPO config:** β=0 (no KL), asymmetric clip ε=[0.2, 0.25], G=8 completions/prompt, temp=0.9, top_p=0.95, + lr=1e-5. Problems: 6k execution-verifiable (problem_solving + spec_to_code) + abstention records. + +## Benchmarks (greedy pass@1, same Colab/evalplus harness for all three) + +| Metric | base | SFT (`MoM-python-slm`) | **this model (GRPO)** | GRPO vs SFT | +|---|---|---|---|---| +| MBPP | 66.7 | 69.6 | **72.5** | **+2.9** | +| MBPP+ | — | — | 62.7 | — | +| domain `problem_solving` (exec) | 0.700 | 0.713 | **0.767** | **+5.4** | +| domain `spec_to_code` (exec) | 0.632 | 0.714 | **0.729** | +1.5 | +| domain `api_usage` (application) | — | 0.855 | **0.900** | +4.5 | +| HumanEval | 68.9 | 70.7 | 67.7 | −3.0 | +| HumanEval+ | — | — | 62.2 | — | +| domain `api_signature` (param-recall) | 0.217 | 0.299 | 0.301 | +0.0 | + +## What GRPO did (load-bearing read) + +GRPO is a **specialization trade, not a free lunch.** Gains land on exactly the execution-rewarded, +spec-driven dimensions — **MBPP +2.9** and **domain problem_solving +5.4** over SFT — while the +**un-reinforced HumanEval completion format gives back −3.0** (slightly under base). That's the textbook +RLVR signature: the model sharpens "write a correct function from a spec" (what the MoM node actually +does) at a small cost to "graft a body under a fixed signature" (a format it never saw a reward for). + +- **Use this model** for the spec-driven node role — it's the strongest on MBPP and the held-out domain eval. +- **Use the [SFT sibling](https://huggingface.co/srivarenya/MoM-python-slm)** if HumanEval-completion is a + hard gate — it remains the HumanEval-strongest checkpoint (70.7). + +## Usage +```python +from transformers import AutoModelForCausalLM, AutoTokenizer +tok = AutoTokenizer.from_pretrained("srivarenya/MoM-python-slm-grpo") +model = AutoModelForCausalLM.from_pretrained( + "srivarenya/MoM-python-slm-grpo", dtype="bfloat16", device_map="auto") +``` +Prompt with the training system prompt + a Python task; the model returns reasoning then code. Reward, +training recipe, and the self-contained GRPO Colab notebook are in the project repository. + +Next cross-check: **LiveCodeBench** (contamination-resistant), before/after vs the SFT sibling. 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..d76d991 --- /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": 28, + "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": "5.12.1", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..8ae691b --- /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": "5.12.1" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..c368019 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:815cc454a67c91983e0b3f19dc21d444d87a2c47f91b72fd815f39c86448b562 +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..29ee655 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,31 @@ +{ + "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, + "local_files_only": false, + "model_max_length": 32768, + "pad_token": "<|endoftext|>", + "padding_side": "left", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}