Upload README.md with huggingface_hub

README.md

@@ -2,206 +2,215 @@
 base_model: google/gemma-2-2b-it
 library_name: peft
 pipeline_tag: text-generation
+language:
+- ja
+- en
 tags:
-- base_model:adapter:google/gemma-2-2b-it
 - lora
 - transformers
+- game-strategy
+license: apache-2.0
 ---
 
-# Model Card for Model ID
+# Gemma-2-2B-IT ゲーム戦略ファインチューニングモデル
+
+## モデル概要
+
+このモデルは、Googleの[Gemma-2-2B-IT](https://huggingface.co/google/gemma-2-2b-it)をベースに、22個のゲーム戦略知識をLoRA（Low-Rank Adaptation）でファインチューニングしたものです。
+
+**学習内容:**
+- 5つの基本戦略タイプ（Offensive, Defensive, Adaptive, Disruptive, Endurance）
+- 7つの攻撃側決定基準（Cumulative Probability Focus, Recent Pattern Focus, Speed Focus, Return Focus, Feint Focus, Distribution Focus, Energy Efficiency Focus）
+- 7つの防御側決定基準（Cumulative Probability Focus, Recent Pattern Focus, Counterattack Focus, Return Focus, Risk Avoidance Focus, Counter Focus, Distribution Focus）
+
+## 訓練情報
+
+### 訓練データ
+- **データ数**: 479件（訓練）+ 25件（検証）
+- **データソース**: game_rules_augmented.jsonl
+- **データ形式**: Gemma-2-itプロンプトテンプレート形式
+  ```
+  <start_of_turn>user
+  質問<end_of_turn>
+  <start_of_turn>model
+  回答<end_of_turn>
+  ```
+
+### ハイパーパラメータ
+| パラメータ | 値 |
+|-----------|-----|
+| ベースモデル | google/gemma-2-2b-it |
+| LoRAランク (r) | 16 |
+| LoRA alpha | 32 |
+| LoRA dropout | 0.1 |
+| ターゲットモジュール | q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj |
+| 学習率 | 5e-5 |
+| バッチサイズ | 2 x 8 (gradient accumulation) = 16 |
+| エポック数 | 37（途中停止） |
+| 最適化手法 | AdamW |
+| Warmup ratio | 0.3 |
+| Weight decay | 0.05 |
+| 精度 | bfloat16 |
+
+### 訓練結果
+- **最終訓練ロス**: 0.0
+- **最終検証ロス**: 1.08e-05
+- **訓練可能パラメータ**: 20,766,720 (0.79%)
+- **訓練時間**: 約1.5時間
+- **ハードウェア**: NVIDIA RTX 4070 Ti SUPER (16GB VRAM)
+
+## 評価結果
+
+### テスト結果サマリー
+9つの異なる質問でテストを実施：
+
+| 評価 | 件数 | 割合 |
+|------|------|------|
+| ✅ 完璧な回答 | 4/9 | 44% |
+| ⚠️ 部分的に正確 | 1/9 | 11% |
+| ❌ 不正確 | 4/9 | 44% |
+
+### 強み
+✅ **個別の決定基準の説明は非常に正確**
+- Recent Pattern Focus, Counterattack Focus, Counter Focus, Distribution Focusの説明は完璧
+
+✅ **質問の表現バリエーションに対応**
+- "What is", "Explain", "Describe", "Tell me about" など様々な動詞に対応可能
+
+### 弱点
+❌ **過学習による知識の混同**
+- 数値の誤認（5個の戦略を7個と回答）
+- 攻撃側/防御側の混同
+- 戦略特徴の混入
+
+❌ **間接的な質問への対応不足**
+- "Which strategy focuses on energy management?" → 不正確な回答
+
+❌ **比較質問への対応不足**
+- 訓練データに比較形式の例がないため、適切な比較ができない
+
+## 使い方
+
+### インストール
+```bash
+pip install transformers peft torch
+```
+
+### 基本的な使用方法
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+import torch
+
+# ベースモデルとLoRAアダプタをロード
+base_model = AutoModelForCausalLM.from_pretrained(
+    "google/gemma-2-2b-it",
+    device_map="auto",
+    torch_dtype=torch.bfloat16
+)
+
+model = PeftModel.from_pretrained(base_model, "ayousanz/gemma-2-2b-it-game-ft")
+tokenizer = AutoTokenizer.from_pretrained("ayousanz/gemma-2-2b-it-game-ft")
+
+# 推論
+prompt = "What is the offensive strategy?"
+formatted_prompt = f"<start_of_turn>user\n{prompt}<end_of_turn>\n<start_of_turn>model\n"
+
+inputs = tokenizer(formatted_prompt, return_tensors="pt").to(model.device)
+outputs = model.generate(
+    **inputs,
+    max_new_tokens=150,
+    do_sample=False,
+    pad_token_id=tokenizer.pad_token_id,
+    eos_token_id=tokenizer.eos_token_id
+)
+
+response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
+print(response)
+# 出力: Offensive strategy: High risk, high reward strategy type with frequent attacks.
+```
+
+### マージして使用（推奨）
+```python
+# LoRAアダプタをベースモデルにマージ
+merged_model = model.merge_and_unload()
+
+# 推論（より高速）
+inputs = tokenizer(formatted_prompt, return_tensors="pt").to(merged_model.device)
+outputs = merged_model.generate(**inputs, max_new_tokens=150)
+```
+
+## 推奨される使用方法
+
+### ✅ 適している質問
+- 個別の戦略や決定基準の説明
+  - "What is Recent Pattern Focus in offense?"
+  - "Explain Counterattack Focus in defense"
+- 基本的な戦略タイプの説明
+  - "What is the offensive strategy?"
+  - "Tell me about Disruptive strategy"
+
+### ❌ 避けるべき質問
+- 数を問う質問
+  - "How many basic strategy types are there?" → 不正確な可能性
+- 比較質問
+  - "Compare offensive and defensive strategies" → 不適切な回答
+- 間接的な質問
+  - "Which strategy focuses on X?" → 不正確な可能性
+
+## 制限事項と注意点
+
+### ⚠️ 過学習について
+このモデルはエポック37で訓練されており、**過学習**の兆候があります：
+- 訓練ロスが0.0まで低下
+- 一部の知識が混同（数値、攻撃/防御の区別）
+- 訓練データにない造語を生成する場合あり
+
+### 推奨事項
+より正確なモデルが必要な場合は、以下のアプローチを推奨：
+1. **エポック数を10-15に削減して再訓練**
+2. **データの追加**（比較質問、間接質問の例を追加）
+3. **正則化の強化**（weight decay増加、LoRA dropout増加）
+
+## ライセンス
+
+このモデルは以下のライセンスに従います：
+- **コード**: MIT License
+- **ベースモデル（Gemma-2）**: [Gemma Terms of Use](https://ai.google.dev/gemma/terms)に従ってください
+
+## 引用
+
+このモデルを使用する場合は、以下を引用してください：
+
+```bibtex
+@misc{gemma-2-2b-it-game-ft,
+  author = {ayousanz},
+  title = {Gemma-2-2B-IT Game Strategy Fine-tuning},
+  year = {2025},
+  publisher = {Hugging Face},
+  howpublished = {\url{https://huggingface.co/ayousanz/gemma-2-2b-it-game-ft}}
+}
+```
+
+## 技術仕様
+
+### モデルアーキテクチャ
+- **ベースモデル**: Gemma-2-2B-IT
+- **ファインチューニング手法**: LoRA (Low-Rank Adaptation)
+- **パラメータ効率**: 0.79% (20.7M / 2.6B)
+
+### 計算環境
+- **GPU**: NVIDIA RTX 4070 Ti SUPER (16GB VRAM)
+- **OS**: Windows 11
+- **フレームワーク**:
+  - Transformers 4.47.1
+  - PEFT 0.17.1
+  - PyTorch 2.5.1+cu124
+
+## 連絡先
+
+問題や質問がある場合は、[Issues](https://huggingface.co/ayousanz/gemma-2-2b-it-game-ft/discussions)でお知らせください。
 
-<!-- Provide a quick summary of what the model is/does. -->
-
-
-
-## Model Details
-
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
-### Framework versions
+---
 
-- PEFT 0.17.1
+**🤖 このモデルは実験的なものです。本番環境での使用前に十分なテストを行ってください。**