commit 0f67dbbfa3d4c9a0be191df43e07eb99bb1cc9c7 Author: ModelHub XC Date: Wed Jul 22 01:02:11 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: seanpoyner/smolcode-coder-orchestrate-3b-tools Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..84f33df --- /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 +tokenizer.json filter=lfs diff=lfs merge=lfs -text +smolcode-coder-orchestrate-3b-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..eb0c797 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +license: apache-2.0 +base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct +tags: +- code +- function-calling +- tool-use +- agent +- small-language-model +datasets: +- NousResearch/hermes-function-calling-v1 +language: +- en +pipeline_tag: text-generation +--- + +# smolcode-coder-1.5b-tools + +A LoRA fine-tune of **Qwen2.5-Coder-1.5B-Instruct** that teaches the model to emit +**native `` function calls**, so a 1.5B *coder* model can actually drive an +agentic write → run → fix → verify loop. + +Built for [**smolcode**](https://gitea.poyner.ai/sean/smolcode) — an SLM-optimized +agentic coding assistant — for the Hugging Face **Build Small** hackathon. + +## Why +Out of the box, small Qwen-Coder models describe tool calls as plain-text/```json +instead of emitting the native `` token (id 151657) that runtimes (Ollama, +llama.cpp) parse into OpenAI-style `tool_calls` — which breaks agentic loops. This +fine-tune closes that gap on a tiny (1.5B) model: **100% native `` emission** +in free generation on held-out prompts (base model: 0%). + +## Results +- **Native tool-call rate:** 100% (16/16 held-out prompts) — the release gate. +- **Agentic bench (smolcode pass@1, 10 tasks):** 9/10 as the entry tier of a + 1.5B→8B→30B ladder, solving **7/10 entirely on its own** (2–16s each). For + comparison the all-Granite ladder (3B entry) scores 10/10 — the 1.5B carries the + same standalone load as a 2×-larger 3B. +- **Train loss:** 0.138 (3 epochs, assistant-only loss). + +## Training +- **Base:** Qwen/Qwen2.5-Coder-1.5B-Instruct +- **Method:** bf16 LoRA (r=16, α=32) on attention + MLP projections, **plus full + training of `embed_tokens` + `lm_head`** (`modules_to_save`) — required so the model + can *output* the `` special token, which LoRA on attention/MLP alone + cannot. **Assistant-only loss** (loss on tool calls + final answers only). +- **Data:** NousResearch/hermes-function-calling-v1 (breadth) + synthetic smolcode + tool-use trajectories (sharpness), all rendered through the *same* + `apply_chat_template(tools=...)` used at inference — training target is byte-identical + to the served prompt (fixes the v1 train/inference template mismatch). +- **Schedule:** 3 epochs, full 2048 sequence length. Trained on Modal (A100). + +## Serving — read this, two non-obvious requirements +1. **Serve via the GGUF, not the safetensors directly.** Ollama's bf16-safetensors + auto-import produces garbage (`??????`) for this model. Use the included + `smolcode-1.5b-q4_k_m.gguf` (converted with llama.cpp `convert_hf_to_gguf.py`): + ```bash + ollama create smolcode-coder-1.5b:tools -f Modelfile # Modelfile is in this repo + ``` +2. **`repeat_penalty` / `repetition_penalty` MUST be 1.0.** The tool system prompt + literally contains the `` token, so any penalty > 1 suppresses the model + from emitting it (you'll see a stray token + bare JSON instead). The included + `Modelfile` sets `PARAMETER repeat_penalty 1.0`. For raw `transformers.generate`, + pass `repetition_penalty=1.0`. + +With those, Ollama's `/v1/chat/completions` returns proper native `tool_calls`. + +## Use (transformers) +Standard Qwen2.5 chat template with `tools=`; greedy, `repetition_penalty=1.0`. The +model responds with `{"name": ..., "arguments": ...}`. + +## Files +- `model.safetensors` + tokenizer/config — the merged model (lm_head untied). +- `smolcode-1.5b-q4_k_m.gguf` — quantized GGUF for serving. +- `Modelfile` — Ollama import recipe (template + `repeat_penalty 1.0`). + +## License +Apache-2.0 (inherits from the base model). 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..1382901 --- /dev/null +++ b/config.json @@ -0,0 +1,69 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "bfloat16", + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 11008, + "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", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 36, + "model_type": "qwen2", + "num_attention_heads": 16, + "num_hidden_layers": 36, + "num_key_value_heads": 2, + "pad_token_id": null, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": false, + "transformers_version": "5.12.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..ded3a63 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "repetition_penalty": 1.05, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.12.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..3fc4ffd --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a43174cfdd29d9668437f2c92dac69678da5f5fab59529ca61450b1692bd8d5 +size 6794257120 diff --git a/smolcode-coder-orchestrate-3b-q4_k_m.gguf b/smolcode-coder-orchestrate-3b-q4_k_m.gguf new file mode 100644 index 0000000..00d4104 --- /dev/null +++ b/smolcode-coder-orchestrate-3b-q4_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8e61be33491598f8190215722f2832f7f025b46efd156c4906cf0df8339ebbf +size 2104933568 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..5156d16 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,30 @@ +{ + "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|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}