Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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

README.md

@@ -0,0 +1,154 @@
+這是NYCU深度學習課程KAGGLE #3的模型，使用Qwen2.5-7B-Instruct進行GRPO（Group Relative Policy Optimization）強化學習訓練，專注於提升模型回答的中立性和推理品質。
+
+## 模型資訊
+
+* **基礎模型**: Qwen/Qwen2.5-7B-Instruct
+* **微調方法**: LoRA (r=16, alpha=32) + GRPO
+* **任務**: 中文單選題問答（強調中立性推理）
+* **訓練數據**: 英文翻譯版推理數據（約10,500條，佔總數據35%）
+* **特色**: 中立性優化、減少偏見、多角度思考
+
+## 主要特點
+
+1. **中立性增強**: 透過GRPO訓練，中立性分數達到0.82（滿分1.0）
+2. **推理一致性**: 不同提示下的答案一致性達88%
+3. **減少偏見**: 顯著降低絕對化用詞和情緒化表達
+4. **多角度分析**: 訓練模型從多個視角考慮問題
+
+## 使用方法
+
+### 基本使用
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from peft import PeftModel
+import torch
+
+# 載入基礎模型
+base_model = AutoModelForCausalLM.from_pretrained(
+    \"Qwen/Qwen2.5-7B-Instruct\",
+    torch_dtype=torch.float16,
+    device_map=\"auto\",
+    trust_remote_code=True
+)
+
+# 載入GRPO微調的LoRA
+model = PeftModel.from_pretrained(
+    base_model, 
+    \"RayTsai/Kaggle_3_GRPO_Neutrality\"
+)
+
+# 載入tokenizer
+tokenizer = AutoTokenizer.from_pretrained(\"Qwen/Qwen2.5-7B-Instruct\")
+
+# 使用中立性提示
+prompt = \"\"\"請從多元視角分析以下問題：
+
+問題：{your_question}
+
+選項：
+A. {option_a}
+B. {option_b}
+C. {option_c}
+D. {option_d}
+
+請提供平衡的分析，考慮不同觀點後給出答案。\"\"\"
+
+# 生成回答
+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
+)
+response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+```
+
+### 兩階段推理系統（推薦）
+
+為了獲得最佳效果，建議使用兩階段推理系統：
+
+```python
+# Stage 1: 使用GRPO模型生成詳細推理
+reasoning = generate_reasoning_with_grpo(question, options)
+
+# Stage 2: 使用專門的提取器獲取答案
+final_answer = extract_answer_from_reasoning(reasoning)
+```
+
+## 訓練細節
+
+* **訓練方法**: Group Relative Policy Optimization (GRPO)
+* **訓練時長**: 84小時（RTX 4090）
+* **數據規模**: 10,500條（總數據的35%）
+* **批次大小**: 16（梯度累積=2，有效批次=32）
+* **學習率**: 3e-5
+* **Epochs**: 2
+
+## 性能指標
+
+| 指標 | 數值 |
+|------|------|
+| 中立性分數 | 0.82 |
+| 推理一致性 | 88% |
+| Private準確率 | ~0.45 |
+| Public/Private差距 | 0.10 |
+| 平均獎勵分數 | 0.75 |
+
+## 中立性改善示例
+
+**改善前（標準回答）**：
+```
+答案絕對是C！其他選項都是錯誤的。
+```
+
+**改善後（中立回答）**：
+```
+從不同角度分析這個問題：
+- 選項A關注了X方面，有其合理性
+- 選項B強調了Y維度，也值得考慮
+- 選項C在當前語境下可能更為平衡
+- 選項D提供了另一種視角
+
+綜合各方觀點，選項C可能是相對合理的選擇，
+但這並不否定其他選項在特定情況下的價值。
+```
+
+## 注意事項
+
+1. **輸出格式**: GRPO模型的輸出格式可能不夠穩定，建議使用提供的答案提取工具
+2. **推理長度**: 模型傾向生成較長的推理，可能需要設置適當的max_new_tokens
+3. **語言一致性**: 雖然使用英文數據訓練，但推理時使用中文效果更好
+
+## 引用
+
+如果您使用了這個模型，請引用：
+
+```bibtex
+@misc{tsai2025chinese_grpo,
+  title={Chinese LLM with GRPO-based Neutrality Optimization},
+  author={Ray Tsai},
+  year={2025},
+  publisher={Hugging Face},
+  journal={Hugging Face Model Hub},
+  howpublished={\\url{https://huggingface.co/RayTsai/Kaggle_3_GRPO_Neutrality}}
+}
+```
+
+## 作者
+
+* Ray Tsai (110651053)
+* NYCU 深度學習課程 2025
+## 授權
+
+本模型遵循Qwen2.5的原始授權條款。
+
+## 相關連結
+
+* [KAGGLE #1 - SFT模型](https://huggingface.co/RayTsai/chinese-llm-mcq-qwen2-5-14b)
+* [KAGGLE #2 - 推理鏈模型](https://huggingface.co/RayTsai/Kaggle_2)
+* [技術報告](https://github.com/RayTsai/chinese-llm-neutrality)
+* [NYCU深度學習課程](https://www.nycu.edu.tw)`
+}

adapter_config.json

@@ -0,0 +1,36 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:809de0a64f08802c153e961a7610bf183aa0426dbd7697688ea2f88f72d402f6
+size 40400200

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

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 <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|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<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- 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 %}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_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|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
+size 11422063

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_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|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b8d30a4ff2d322236370ebfabd1801b1e34253bf27dd0476315f15a8984f0ef
+size 6801