commit 8869dc8f539eeb46856dba2b7b25255437c47193 Author: ModelHub XC Date: Tue Jul 28 22:43:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: DhruvalLabs/qwen3-8b-claude-agentic-fable5 Source: Original Platform 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..7648431 --- /dev/null +++ b/README.md @@ -0,0 +1,213 @@ +--- +license: apache-2.0 +base_model: Qwen/Qwen3-8B +tags: + - qwen3 + - agentic + - coding-agent + - tool-use + - finetuned + - lora + - unsloth + - fable5 + - claude +language: + - en +pipeline_tag: text-generation +library_name: transformers +--- + +# qwen3-8b-claude-agentic-fable5 + +**A Qwen3-8B model fine-tuned on Claude Fable-5 agent traces for agentic coding tasks.** + +Fine-tuned by **DhruvalLabs** using LoRA on real coding agent trajectories from the +[Glint-Research/Fable-5-traces](https://huggingface.co/datasets/Glint-Research/Fable-5-traces) dataset. + +--- + +## What is this model? + +This model is fine-tuned to behave like an **agentic coding assistant** — it reasons step by step +inside `` tags before taking any action, then calls the appropriate tool to complete the task. + +Unlike a standard chat model that just replies with text, this model: +- **Thinks before acting** — every response includes a reasoning chain +- **Calls tools correctly** — uses `bash`, `read_file`, `write_file`, `edit_file`, `web_search` and more +- **Works multi-step** — plans and executes complex tasks autonomously +- **Follows the Fable-5 agent style** — trained on real Claude Fable-5 coding sessions + +--- + +## Training Details + +| | | +|---|---| +| **Base model** | `Qwen/Qwen3-8B` | +| **Dataset** | `Glint-Research/Fable-5-traces` | +| **Dataset size** | 4,665 rows | +| **Method** | QLoRA (LoRA fine-tuning on 4-bit quantized model) | +| **LoRA rank** | 16 | +| **LoRA alpha** | 32 | +| **Target modules** | q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj | +| **Training steps** | 580 | +| **Batch size** | 2 × 8 grad accum = 16 effective | +| **Learning rate** | 2e-4 | +| **Sequence length** | 8192 | +| **GPU** | NVIDIA RTX 4000 Ada (20GB) | +| **Framework** | Unsloth + TRL | +| **Final loss** | ~0.27 | + +--- + +## What it learned + +The model was trained on real Fable-5 (Claude) coding agent sessions. Each training example contains: +- A coding task from a real user +- The agent's step-by-step reasoning (`` block) +- The tool call the agent made (`bash`, `read_file`, `write_file`, etc.) + +Tools present in training data: + +| Tool | Count | +|---|---| +| bash | 1,544 | +| edit_file | 960 | +| text_response | 866 | +| read_file | 443 | +| write_file | 311 | +| web_search | 72 | +| + others | ~200 | + +--- + +## How to use + +### Basic inference + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer +import torch + +model = AutoModelForCausalLM.from_pretrained( + "DhruvalLabs/qwen3-8b-claude-agentic-fable5", + torch_dtype=torch.bfloat16, + device_map="auto", +) +tokenizer = AutoTokenizer.from_pretrained("DhruvalLabs/qwen3-8b-claude-agentic-fable5") + +messages = [ + { + "role": "system", + "content": ( + "You are an expert agentic coding assistant. " + "Before every action, reason carefully inside ... tags. " + "Then call the appropriate tool to complete the task step by step." + ) + }, + { + "role": "user", + "content": "/think\nRead the file main.py and summarize what it does." + } +] + +inputs = tokenizer.apply_chat_template( + messages, + tokenize=True, + add_generation_prompt=True, + return_tensors="pt" +).to("cuda") + +outputs = model.generate( + input_ids=inputs, + max_new_tokens=500, + temperature=0.7, + do_sample=True, +) +print(tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True)) +``` + +### With Unsloth (faster, less VRAM) + +```python +from unsloth import FastLanguageModel + +model, tokenizer = FastLanguageModel.from_pretrained( + model_name = "DhruvalLabs/qwen3-8b-claude-agentic-fable5", + max_seq_length = 8192, + load_in_4bit = True, +) +FastLanguageModel.for_inference(model) +``` + +### With vLLM (for serving as API) + +```bash +python -m vllm.entrypoints.openai.api_server \ + --model DhruvalLabs/qwen3-8b-claude-agentic-fable5 \ + --port 8000 \ + --max-model-len 8192 +``` + +Then connect any OpenAI-compatible client to `http://localhost:8000/v1`. + +--- + +## Example output + +**Input:** +``` +Check if Node.js is installed and what version it is. +``` + +**Output:** +``` + +{"name": "bash", "arguments": {"command": "node --version 2>/dev/null || echo 'Node.js not installed'"}} + +``` + +--- + +## Tips for best results + +- Always add `/think` at the start of your user message to trigger reasoning mode +- Use a system prompt that tells the model it's an agentic assistant +- Set `temperature=0.7` for a good balance of creativity and consistency +- Set `max_new_tokens` to at least 400 for complex tasks + +--- + +## Dataset + +Trained on [Glint-Research/Fable-5-traces](https://huggingface.co/datasets/Glint-Research/Fable-5-traces) — +a dataset of real Fable-5 (Claude) coding agent traces converted to Qwen3 chat format. + +Data preprocessing and format conversion done by **DhruvalLabs**. + +--- + +## License + +This model inherits the **Apache 2.0** license from the base Qwen3-8B model. +Free to use for personal, research, and commercial purposes. + +--- + +## Citation + +If you use this model in your research or project, please cite: + +```bibtex +@misc{dhruval2026qwen3fable5, + author = {DhruvalLabs}, + title = {qwen3-8b-claude-agentic-fable5: Qwen3-8B Fine-tuned on Fable-5 Agent Traces}, + year = {2026}, + publisher = {HuggingFace}, + url = {https://huggingface.co/DhruvalLabs/qwen3-8b-claude-agentic-fable5} +} +``` + +--- + +*Made with ❤️ by DhruvalLabs* \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..01be9b3 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,89 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {{- messages[0].content + '\n\n' }} + {%- endif %} + {{- "# 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' }} + {%- 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" and message.content is string and not(message.content.startswith('') and message.content.endswith('')) %} + {%- set ns.multi_step_tool = false %} + {%- set ns.last_query_index = index %} + {%- endif %} +{%- endfor %} +{%- for message in messages %} + {%- if message.content is string %} + {%- set content = message.content %} + {%- else %} + {%- set content = '' %} + {%- endif %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} + {{- '<|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 %} + {%- if loop.index0 > ns.last_query_index %} + {%- if loop.last or (not loop.last and reasoning_content) %} + {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content.strip('\n') + '\n\n\n' + content.lstrip('\n') }} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- 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' }} + {%- if enable_thinking is defined and enable_thinking is false %} + {{- '\n\n\n\n' }} + {%- endif %} +{%- endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..38abad0 --- /dev/null +++ b/config.json @@ -0,0 +1,72 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "bfloat16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 12288, + "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": 40960, + "max_window_layers": 36, + "model_type": "qwen3", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "pad_token_id": 151643, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": false, + "transformers_version": "5.5.0", + "unsloth_version": "2026.6.9", + "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..adb108e --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "max_length": 40960, + "pad_token_id": 151643, + "temperature": 0.6, + "top_k": 20, + "top_p": 0.95, + "transformers_version": "5.5.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..0948fe7 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef8cb9cb9ea56e34457bdd154cd9e94d980377fd20a243f7568d22a7b66c2137 +size 16381517208 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..10c92fa --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:476870a1f2fb6f6a2759a6ede2383bf9d5d738f17844563b65c91965b722ae09 +size 11422924 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..6bfa918 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,226 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": [], + "is_local": true, + "model_max_length": 40960, + "pad_token": "<|endoftext|>", + "padding_side": "left", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151657": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151658": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151665": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151666": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151667": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151668": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + } + } +}