commit ef53f4cc43e7f3697c4d139e7da2366ace68d9b6 Author: ModelHub XC Date: Fri Sep 11 07:44:14 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: micymike/CodeMate-Qwen-1.5B-32K-Distilled-on-Claude-Fable-5 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..b6b8f85 --- /dev/null +++ b/README.md @@ -0,0 +1,141 @@ +--- +license: apache-2.0 +base_model: micymike/codemate-qwen-1.5B-8k +tags: +- code +- coding +- qwen +- qwen2 +- transformers +- text-generation +- distillation +- 32k-context +- software-engineering +- chat +pipeline_tag: text-generation +language: +- en +--- + +# CodeMate-Qwen-1.5B-32K-Distilled-on-Claude-Fable-5 + +CodeMate-Qwen-1.5B-32K-Distilled-on-Claude-Fable-5 is a fine-tuned coding assistant built on top of **CodeMate-Qwen-1.5B-8K**. + +The model was further trained on converted Claude Fable 5 coding traces to improve: + +- Code generation +- Code explanation +- Debugging +- Multi-turn coding conversations +- Software engineering reasoning + +## Model Details + +- **Base Model:** `micymike/codemate-qwen-1.5B-8k` +- **Architecture:** Qwen2 Causal LM +- **Training Method:** LoRA fine-tuning merged into full weights +- **Precision:** BF16 +- **Configured Context Length:** 32,768 tokens + +## Context Configuration + +This model has been configured for a 32K context window using YaRN RoPE scaling. + +```python +from transformers import AutoConfig + +config = AutoConfig.from_pretrained( + "micymike/CodeMate-Qwen-1.5B-32K-Distilled-on-Claude-Fable-5" +) + +print(config.max_position_embeddings) +print(config.rope_scaling) +``` + +Current configuration: + +```python +{ + "rope_type": "yarn", + "factor": 4.0, + "original_max_position_embeddings": 8192, + "rope_theta": 1000000.0 +} +``` + +Note: Long-context performance beyond the original context length should be evaluated carefully for specific workloads. + +## Dataset + +The model was trained on converted Claude Fable 5 coding traces formatted into OpenAI-style conversations. + +## Usage + +```python +from transformers import AutoTokenizer, AutoModelForCausalLM +import torch + +model_id = "micymike/CodeMate-Qwen-1.5B-32K-Distilled-on-Claude-Fable-5" + +tokenizer = AutoTokenizer.from_pretrained(model_id) + +model = AutoModelForCausalLM.from_pretrained( + model_id, + torch_dtype=torch.bfloat16, + device_map="auto" +) + +messages = [ + { + "role": "system", + "content": "You are CodeMate, an expert programming assistant." + }, + { + "role": "user", + "content": "Write a Python function to compute edit distance." + } +] + +prompt = tokenizer.apply_chat_template( + messages, + tokenize=False, + add_generation_prompt=True, +) + +inputs = tokenizer(prompt, return_tensors="pt").to(model.device) + +outputs = model.generate( + **inputs, + max_new_tokens=512, + temperature=0.7, + top_p=0.9, + do_sample=True +) + +print(tokenizer.decode(outputs[0], skip_special_tokens=True)) +``` + +## Limitations + +* Experimental research model. +* Long-context capabilities require further evaluation. +* May generate incorrect or insecure code. + +## Acknowledgements + +Built upon: + +* Qwen2 +* Transformers +* PEFT +* Hugging Face +* llama.cpp +* Claude Fable traces + +## Disclaimer + +This project is an independent research effort and is not affiliated with or endorsed by Anthropic, Claude, Alibaba, or Qwen. + +## Author + +Built by **micymike** 🇰🇪 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..dab6a36 --- /dev/null +++ b/config.json @@ -0,0 +1,65 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": null, + "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": 32768, + "max_window_layers": 28, + "model_type": "qwen2", + "num_attention_heads": 12, + "num_hidden_layers": 28, + "num_key_value_heads": 2, + "pad_token_id": 151665, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "factor": 4.0, + "original_max_position_embeddings": 8192, + "rope_theta": 1000000.0, + "rope_type": "yarn" + }, + "rope_theta": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "5.12.1", + "unsloth_version": "2026.6.8", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..f6a7c42 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,9 @@ +{ + "eos_token_id": [ + 151643 + ], + "max_length": 32768, + "max_new_tokens": 2048, + "pad_token_id": 151665, + "transformers_version": "5.12.1" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..1688eca --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecde8040a53861c161f139a036d3f1c7c8a615e198f88215c729366f8f4c46b3 +size 3087467144 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..5340d81 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31 +size 11422356 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..7d046ea --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,17 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|endoftext|>", + "errors": "replace", + "extra_special_tokens": [], + "is_local": false, + "local_files_only": false, + "model_max_length": 32768, + "pad_token": "<|PAD_TOKEN|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}