commit ef81e726c267e80436f321b7d71b4eae90753b1c Author: ModelHub XC Date: Tue Aug 4 01:25:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: vishnuamarapu/Full-Fine-Tuning-Qwen-2.5-0.5B-instruct-sft 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..b773533 --- /dev/null +++ b/README.md @@ -0,0 +1,223 @@ +--- +license: apache-2.0 +language: + - en +pipeline_tag: text-generation +library_name: transformers +base_model: Qwen/Qwen2.5-0.5B-Instruct +tags: + - qwen + - llm + - sft + - conversational + - transformers + - pytorch +--- + +# Supervised Fine-Tuned Qwen2.5-0.5B-Instruct (SFT) + +This repository contains a **Supervised Fine-Tuned (SFT)** version of **Qwen2.5-0.5B-Instruct**. The model has been fine-tuned on a custom instruction-following conversational dataset to answer questions about Vishnu in a natural and helpful manner. + +## Model Details + +* **Base Model:** `Qwen/Qwen2.5-0.5B-Instruct` +* **Training Method:** Supervised Fine-Tuning (SFT) +* **Framework:** Hugging Face Transformers +* **Task:** Conversational Text Generation + +--- + +# Installation + +```bash +pip install transformers accelerate torch +``` + +--- + +# Loading the Model + +```python +from transformers import AutoTokenizer, AutoModelForCausalLM +import torch + +MODEL_ID = "vishnuamarapu/Full-Fine-Tuning-Qwen-2.5-0.5B-instruct-sft" + +tokenizer = AutoTokenizer.from_pretrained(MODEL_ID) + +model = AutoModelForCausalLM.from_pretrained( + MODEL_ID, + torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32, + device_map="auto" +) +``` + +--- + +# Example Inference + +```python +messages = [ + { + "role": "system", + "content": ( + "You are Vishnu's personal AI assistant. " + "Answer questions about Vishnu using the provided information." + ) + }, + { + "role": "user", + "content": "Tell me about Vishnu." + } +] + +text = tokenizer.apply_chat_template( + messages, + tokenize=False, + add_generation_prompt=True +) + +inputs = tokenizer( + text, + return_tensors="pt" +).to(model.device) + +outputs = model.generate( + **inputs, + max_new_tokens=256 +) + +response = tokenizer.decode( + outputs[0][inputs.input_ids.shape[-1]:], + skip_special_tokens=True +) + +print(response) +``` + +--- + +# Gradio Demo + +```python +import gradio as gr +from transformers import AutoTokenizer, AutoModelForCausalLM +import torch + +MODEL_ID = "vishnuamarapu/Full-Fine-Tuning-Qwen-2.5-0.5B-instruct-sft" + +tokenizer = AutoTokenizer.from_pretrained(MODEL_ID) + +model = AutoModelForCausalLM.from_pretrained( + MODEL_ID, + torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32, + device_map="auto" +) + +def chat(message, history): + + messages = [ + { + "role": "system", + "content": ( + "You are Vishnu's personal AI assistant. " + "Answer questions about Vishnu using the provided information." + ) + } + ] + + for user, assistant in history: + messages.append({"role": "user", "content": user}) + messages.append({"role": "assistant", "content": assistant}) + + messages.append({"role": "user", "content": message}) + + text = tokenizer.apply_chat_template( + messages, + tokenize=False, + add_generation_prompt=True + ) + + inputs = tokenizer( + text, + return_tensors="pt" + ).to(model.device) + + outputs = model.generate( + **inputs, + max_new_tokens=256 + ) + + response = tokenizer.decode( + outputs[0][inputs.input_ids.shape[-1]:], + skip_special_tokens=True + ) + + return response + +gr.ChatInterface(chat).launch() +``` + +--- + +# Generation Parameters + +| Parameter | Value | +| -------------- | ----------------------------: | +| max_new_tokens | 256 | +| device_map | auto | +| torch_dtype | float16 (GPU) / float32 (CPU) | + +--- + +# Repository Structure + +``` +config.json +generation_config.json +model.safetensors +tokenizer.json +tokenizer_config.json +chat_template.jinja +training_args.bin +``` + +--- + +# Training Overview + +This model was fine-tuned using **Supervised Fine-Tuning (SFT)** on a custom instruction-response dataset. + +The training process included: + +* Instruction-response formatting using the Qwen chat template +* Hugging Face Transformers +* TRL SFTTrainer +* PyTorch +* Custom conversational dataset + +--- + +# Citation + +If you use this model in your work, please cite this repository. + +```bibtex +@misc{vishnu_qwen25_sft, + author = {Vishnu Amarapu}, + title = {Supervised Fine-Tuned Qwen2.5-0.5B-Instruct}, + year = {2026}, + publisher = {Hugging Face}, + howpublished = {\url{https://huggingface.co/vishnuamarapu/Full-Fine-Tuning-Qwen-2.5-0.5B-instruct-sft}} +} +``` + +--- + +# Acknowledgements + +* Alibaba Cloud Qwen Team for the base model. +* Hugging Face Transformers. +* TRL (Transformer Reinforcement Learning). +* PyTorch. + 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..7b4bd0d --- /dev/null +++ b/config.json @@ -0,0 +1,57 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 896, + "initializer_range": 0.02, + "intermediate_size": 4864, + "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" + ], + "max_position_embeddings": 32768, + "max_window_layers": 21, + "model_type": "qwen2", + "num_attention_heads": 14, + "num_hidden_layers": 24, + "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": "5.12.0", + "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..b464d5a --- /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": "5.12.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..19202eb --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f03ef8d6640859d0ed8ba08de8131ab699850d70be2b8ac12ee88cd190cec56 +size 988097824 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..770e41d --- /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": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..081d0c9 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4003d54049c876c9d4a279676887cbb251aae88679d1619feb5d0bc282e4cef +size 5649