commit 9519ca1bf65c372de12d1b3f196b8c0d361baa62 Author: ModelHub XC Date: Sat Jun 13 09:32:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: adriangg04/TheLastOfUs-QA 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..481df3b --- /dev/null +++ b/README.md @@ -0,0 +1,177 @@ +--- +license: apache-2.0 +datasets: +- adriangg04/the-last-of-us-instruction-dataset +language: +- en +base_model: +- Qwen/Qwen2.5-7B-Instruct +new_version: Qwen/Qwen2.5-7B-Instruct +pipeline_tag: text-generation +library_name: transformers +tags: +- agent +- text-generation +- question-answering +- the-last-of-us +- qwen +- fine-tuned +model-index: + - name: TheLastOfUs-QA + results: + - task: + type: question-answering + dataset: + name: the-last-of-us-instruction-dataset + type: the-last-of-us-instruction-dataset + metrics: + - name: Evaluation Loss + type: loss + value: 1.011 + - name: Evaluation Entropy + type: entropy + value: 1.011 +--- + +[![GitHub Source Code](https://img.shields.io/badge/GitHub-Source_Code-black?logo=github)](https://github.com/4drian04/qwen-7b-tlou-qa-finetuning) + +# TheLastOfUs-QA: Fine-tuned Model on Qwen2.5-7B-Instructed for The Last of Us + +This model is a fine-tuned version of the base model **Qwen2.5-7B-Instructed**, specifically adapted to answer questions and generate text related to the universe of **The Last of Us**. + +## Description + +The model was trained to understand and generate content about the story, characters, events, and lore of the video game **The Last of Us**. Thanks to fine-tuning with the specialized dataset **the-last-of-us-instruction-dataset**, this model is capable of providing coherent and detailed answers to any query about this universe. + +This model is ideal for: +- Creating conversational assistants that answer questions about The Last of Us. + +- Generate narrative or explanatory content based on the game's lore. + +- Support creative projects related to the post-apocalyptic world of The Last of Us. + +## Training Dataset + +The model was trained using the **the-last-of-us-instruction-dataset**, a custom dataset containing instructions and questions about the game's universe, as well as answers based on the official narrative and key story elements. + +## Training Details + +- **Base model:** Qwen/Qwen2.5-7B-Instruct +- **Method:** QLoRA (4-bit) + PEFT + +**LoRA** +- r=16, alpha=32, dropout=0.05 +- target: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj + +**Training** +- epochs=3, lr=1e-4, scheduler=cosine +- batch=4, grad_accum=4 (effective=16) +- warmup=0.03 + +**Optimization** +- optimizer: paged_adamw_8bit +- bf16 + gradient checkpointing + +**Quantization** +- 4-bit (nf4), double quant, bfloat16 compute + +**Eval & Saving** +- eval/save: each epoch +- best model: eval_loss + +## LoRA Merge + +After fine-tuning, the LoRA adapters were merged into the base model weights. + +### Why merge? + +Merging the LoRA adapters has several advantages: + +- **Simpler usage**: The model can be used directly without loading additional adapters. +- **Better compatibility**: Works seamlessly with standard inference pipelines. +- **Easier deployment**: No need to manage separate LoRA weights. +- **Improved portability**: A single model file is easier to share and integrate. + +### Notes + +- The performance is equivalent to using the LoRA adapters during inference. +- This repository provides the **fully merged model**, ready for immediate use. + +## Hardware + +The model was fine-tuned using: + +- GPU: NVIDIA T4 +- Precision: bfloat16 + 4-bit quantization +- Frameworks: + - Transformers + - PEFT + - TRL (SFTTrainer) + - BitsAndBytes + +## Training Efficiency + +Thanks to QLoRA and 4-bit quantization: + +- Only a small percentage of parameters were trained (LoRA adapters) +- Reduced VRAM usage, enabling training on a single GPU +- Maintained strong performance while being computationally efficient + +## Prompt Format + +This model follows a chat-based format using roles: + +- system +- user +- assistant + +Example: + +messages = [ + {"role": "system", "content": "You are an expert on The Last of Us"}, + {"role": "user", "content": "Who is Ellie?"} +] + +## Example of Use + +You can load the model directly with Transformers: + +```python +from transformers import pipeline, AutoTokenizer + +MODEL_NAME = "adriangg04/TheLastOfUs-QA" + +tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME) + +pipe = pipeline( + "text-generation", + model=MODEL_NAME, + tokenizer=tokenizer, + device_map="auto" +) + +# Prompt de prueba simple +messages = [ + {"role": "system", "content": "You are an expert on The Last of Us"}, + {"role": "user", "content": "What is the main reason for Ellie's journey to Seattle in The Last of Us?"} +] + +prompt = tokenizer.apply_chat_template( + messages, + tokenize=False, + add_generation_prompt=True +) + +response = pipe( + prompt, + max_new_tokens=200, + temperature=0.5 +) + +answer = response[0]["generated_text"] + +print("Prompt:", messages[1]["content"]) +print("Response:", answer) +``` + +**Disclaimer:** This model is not affiliated with, endorsed by, or approved by Naughty Dog, Sony Interactive Entertainment, or PlayStation. All content related to *The Last of Us* is used solely for professional and research purposes. Copyrights and trademarks belong to their respective owners. \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..9840d40 --- /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..3d3eee2 --- /dev/null +++ b/config.json @@ -0,0 +1,61 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "bfloat16", + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 3584, + "initializer_range": 0.02, + "intermediate_size": 18944, + "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": 28, + "num_hidden_layers": 28, + "num_key_value_heads": 4, + "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": "5.2.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..b4315b1 --- /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": "5.2.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..2f89142 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d76de496e2560f1ffca82d8cfb9f2d107337bc67121832ee3f2d8eac48678e5 +size 15231272152 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..d7a13d6 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,29 @@ +{ + "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, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}