Text Generation
PEFT
Safetensors
Transformers
lora
sft
trl
pokemon
pokemon-showdown
gen9ou
action-selection
conversational
Instructions to use hellohazime/qwen3-1p7b-pokellm-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use hellohazime/qwen3-1p7b-pokellm-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-1.7B") model = PeftModel.from_pretrained(base_model, "hellohazime/qwen3-1p7b-pokellm-lora") - Transformers
How to use hellohazime/qwen3-1p7b-pokellm-lora with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="hellohazime/qwen3-1p7b-pokellm-lora") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("hellohazime/qwen3-1p7b-pokellm-lora", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use hellohazime/qwen3-1p7b-pokellm-lora with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "hellohazime/qwen3-1p7b-pokellm-lora" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hellohazime/qwen3-1p7b-pokellm-lora", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/hellohazime/qwen3-1p7b-pokellm-lora
- SGLang
How to use hellohazime/qwen3-1p7b-pokellm-lora with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "hellohazime/qwen3-1p7b-pokellm-lora" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hellohazime/qwen3-1p7b-pokellm-lora", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "hellohazime/qwen3-1p7b-pokellm-lora" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hellohazime/qwen3-1p7b-pokellm-lora", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use hellohazime/qwen3-1p7b-pokellm-lora with Docker Model Runner:
docker model run hf.co/hellohazime/qwen3-1p7b-pokellm-lora
Add/update README (model card)
Browse files
README.md
CHANGED
|
@@ -3,207 +3,198 @@ base_model: Qwen/Qwen3-1.7B
|
|
| 3 |
library_name: peft
|
| 4 |
pipeline_tag: text-generation
|
| 5 |
tags:
|
| 6 |
-
- base_model:adapter:Qwen/Qwen3-1.7B
|
| 7 |
- lora
|
| 8 |
- sft
|
| 9 |
- transformers
|
| 10 |
- trl
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
-
#
|
| 14 |
-
|
| 15 |
-
<!-- Provide a quick summary of what the model is/does. -->
|
| 16 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
|
|
|
|
| 18 |
|
| 19 |
## Model Details
|
| 20 |
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
|
|
|
|
|
|
|
|
|
|
| 26 |
|
| 27 |
-
-
|
| 28 |
-
- **Funded by [optional]:** [More Information Needed]
|
| 29 |
-
- **Shared by [optional]:** [More Information Needed]
|
| 30 |
-
- **Model type:** [More Information Needed]
|
| 31 |
-
- **Language(s) (NLP):** [More Information Needed]
|
| 32 |
-
- **License:** [More Information Needed]
|
| 33 |
-
- **Finetuned from model [optional]:** [More Information Needed]
|
| 34 |
-
|
| 35 |
-
### Model Sources [optional]
|
| 36 |
-
|
| 37 |
-
<!-- Provide the basic links for the model. -->
|
| 38 |
-
|
| 39 |
-
- **Repository:** [More Information Needed]
|
| 40 |
-
- **Paper [optional]:** [More Information Needed]
|
| 41 |
-
- **Demo [optional]:** [More Information Needed]
|
| 42 |
|
| 43 |
## Uses
|
| 44 |
|
| 45 |
-
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 46 |
-
|
| 47 |
### Direct Use
|
|
|
|
|
|
|
| 48 |
|
| 49 |
-
|
| 50 |
-
|
| 51 |
-
|
| 52 |
-
|
| 53 |
-
### Downstream Use [optional]
|
| 54 |
-
|
| 55 |
-
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 56 |
-
|
| 57 |
-
[More Information Needed]
|
| 58 |
-
|
| 59 |
-
### Out-of-Scope Use
|
| 60 |
-
|
| 61 |
-
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 62 |
|
| 63 |
-
|
|
|
|
| 64 |
|
| 65 |
-
|
| 66 |
-
|
| 67 |
-
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 68 |
-
|
| 69 |
-
[More Information Needed]
|
| 70 |
-
|
| 71 |
-
### Recommendations
|
| 72 |
-
|
| 73 |
-
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 74 |
-
|
| 75 |
-
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 76 |
-
|
| 77 |
-
## How to Get Started with the Model
|
| 78 |
|
| 79 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 80 |
|
| 81 |
-
|
| 82 |
|
| 83 |
## Training Details
|
| 84 |
|
| 85 |
### Training Data
|
| 86 |
|
| 87 |
-
|
| 88 |
-
|
| 89 |
-
|
| 90 |
-
|
| 91 |
-
### Training Procedure
|
| 92 |
|
| 93 |
-
|
|
|
|
|
|
|
| 94 |
|
| 95 |
-
###
|
| 96 |
|
| 97 |
-
|
|
|
|
|
|
|
| 98 |
|
|
|
|
| 99 |
|
| 100 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 101 |
|
| 102 |
-
|
| 103 |
|
| 104 |
-
|
| 105 |
-
|
| 106 |
-
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 107 |
-
|
| 108 |
-
[More Information Needed]
|
| 109 |
|
| 110 |
## Evaluation
|
| 111 |
|
| 112 |
-
|
| 113 |
|
| 114 |
-
|
|
|
|
|
|
|
| 115 |
|
| 116 |
-
###
|
| 117 |
|
| 118 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 119 |
|
| 120 |
-
|
|
|
|
| 121 |
|
| 122 |
-
|
| 123 |
-
|
| 124 |
-
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 125 |
-
|
| 126 |
-
[More Information Needed]
|
| 127 |
-
|
| 128 |
-
#### Metrics
|
| 129 |
-
|
| 130 |
-
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 131 |
-
|
| 132 |
-
[More Information Needed]
|
| 133 |
-
|
| 134 |
-
### Results
|
| 135 |
-
|
| 136 |
-
[More Information Needed]
|
| 137 |
-
|
| 138 |
-
#### Summary
|
| 139 |
-
|
| 140 |
-
|
| 141 |
-
|
| 142 |
-
## Model Examination [optional]
|
| 143 |
-
|
| 144 |
-
<!-- Relevant interpretability work for the model goes here -->
|
| 145 |
-
|
| 146 |
-
[More Information Needed]
|
| 147 |
-
|
| 148 |
-
## Environmental Impact
|
| 149 |
-
|
| 150 |
-
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 151 |
-
|
| 152 |
-
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).
|
| 153 |
-
|
| 154 |
-
- **Hardware Type:** [More Information Needed]
|
| 155 |
-
- **Hours used:** [More Information Needed]
|
| 156 |
-
- **Cloud Provider:** [More Information Needed]
|
| 157 |
-
- **Compute Region:** [More Information Needed]
|
| 158 |
-
- **Carbon Emitted:** [More Information Needed]
|
| 159 |
-
|
| 160 |
-
## Technical Specifications [optional]
|
| 161 |
-
|
| 162 |
-
### Model Architecture and Objective
|
| 163 |
-
|
| 164 |
-
[More Information Needed]
|
| 165 |
-
|
| 166 |
-
### Compute Infrastructure
|
| 167 |
-
|
| 168 |
-
[More Information Needed]
|
| 169 |
-
|
| 170 |
-
#### Hardware
|
| 171 |
-
|
| 172 |
-
[More Information Needed]
|
| 173 |
|
| 174 |
-
##
|
| 175 |
|
| 176 |
-
|
|
|
|
|
|
|
|
|
|
| 177 |
|
| 178 |
-
##
|
| 179 |
|
| 180 |
-
|
|
|
|
| 181 |
|
| 182 |
-
|
| 183 |
|
| 184 |
-
|
| 185 |
|
| 186 |
-
|
| 187 |
|
| 188 |
-
|
| 189 |
|
| 190 |
-
##
|
| 191 |
|
| 192 |
-
|
|
|
|
| 193 |
|
| 194 |
-
|
| 195 |
|
| 196 |
-
##
|
| 197 |
|
| 198 |
-
|
|
|
|
| 199 |
|
| 200 |
-
|
| 201 |
|
| 202 |
-
|
| 203 |
|
| 204 |
-
|
| 205 |
|
| 206 |
-
[More Information Needed]
|
| 207 |
### Framework versions
|
| 208 |
|
| 209 |
-
|
|
|
|
|
|
| 3 |
library_name: peft
|
| 4 |
pipeline_tag: text-generation
|
| 5 |
tags:
|
|
|
|
| 6 |
- lora
|
| 7 |
- sft
|
| 8 |
- transformers
|
| 9 |
- trl
|
| 10 |
+
- pokemon
|
| 11 |
+
- pokemon-showdown
|
| 12 |
+
- gen9ou
|
| 13 |
+
- action-selection
|
| 14 |
---
|
| 15 |
|
| 16 |
+
# Qwen3-1.7B PokéLLM LoRA (Gen9 OU / JSON Action Selector)
|
|
|
|
|
|
|
| 17 |
|
| 18 |
+
**Summary:**
|
| 19 |
+
Qwen/Qwen3-1.7B を LoRA で事後学習し、ポケモン Showdown の Gen9 OU 対戦における **単手意思決定**(行動選択)を行う軽量アダプタです。
|
| 20 |
+
本モデルは、与えられた候補集合に対して **厳密 JSON** で `{"action":"index::<k>"}` を返すことを目的に最適化されています。
|
| 21 |
+
(`index::<k>` は、あなたのエージェントが提示する候補リストの 0-based インデックス)
|
| 22 |
|
| 23 |
+
---
|
| 24 |
|
| 25 |
## Model Details
|
| 26 |
|
| 27 |
+
- **Base model:** `Qwen/Qwen3-1.7B`
|
| 28 |
+
- **Adapter type:** LoRA (PEFT)
|
| 29 |
+
- **Task:** Pokémon Showdown Gen9 OU の 1 手意思決定(行動選択)
|
| 30 |
+
- **I/O 仕様:**
|
| 31 |
+
入力: 観測(軽量テキスト or 構造化を文字列化)+候補 `CANDIDATES`(内部で index にマッピング)
|
| 32 |
+
出力: 厳密 JSON 一個 `{ "action": "index::<k>" }`
|
| 33 |
+
- **Intended framework:** 🤗 Transformers + PEFT(PyTorch)
|
| 34 |
+
- **License:** Base モデルに準拠(Qwen/Qwen3-1.7B のライセンスをご確認ください)
|
| 35 |
+
- **Author :** _波浪 創(hellohazime)_
|
| 36 |
|
| 37 |
+
### What this model is / isn’t
|
| 38 |
+
- ✅ **すること**: 候補(技 / 交代など)から **1 つ**を選ぶ。
|
| 39 |
+
- ⚠️ **しないこと**: 一般的な雑談・長文生成・マルチターン方策学習・ダメージ計算の厳密再現。
|
| 40 |
|
| 41 |
+
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
|
| 43 |
## Uses
|
| 44 |
|
|
|
|
|
|
|
| 45 |
### Direct Use
|
| 46 |
+
- 対戦中の観測テキストと、候補キー(内部で `index` に変換したもの)を提示し、**1 手**を選択させる。
|
| 47 |
+
- 出力は **必ず 1 行 1 JSON**。解析側は `action` を読み取り、あなたの `index_map[k]` に解決して実行してください。
|
| 48 |
|
| 49 |
+
### Downstream Use
|
| 50 |
+
- poke-env / Pokémon Showdown クライアントと組み合わせれば、**ローカル対戦エージェント**として利用できます。
|
| 51 |
+
- 学習済みプロンプト・スキーマに依存します。異なるスキーマで使う場合は再学習を推奨。
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
|
| 53 |
+
### Out-of-Scope
|
| 54 |
+
- 一般領域の対話、長文化・推論タスク、Gen9 OU 以外のフォーマットへの強い汎化は想定していません。
|
| 55 |
|
| 56 |
+
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
|
| 58 |
+
## How to Get Started
|
| 59 |
+
|
| 60 |
+
### Load with PEFT (Transformers)
|
| 61 |
+
|
| 62 |
+
```python
|
| 63 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 64 |
+
from peft import PeftModel
|
| 65 |
+
|
| 66 |
+
BASE = "Qwen/Qwen3-1.7B"
|
| 67 |
+
ADAPTER = "YOUR_USERNAME/qwen3-1p7b-pokellm-lora" # ← あなたのリポ名に置換
|
| 68 |
+
|
| 69 |
+
tok = AutoTokenizer.from_pretrained(BASE, trust_remote_code=True)
|
| 70 |
+
if tok.pad_token_id is None and tok.eos_token_id is not None:
|
| 71 |
+
tok.pad_token = tok.eos_token
|
| 72 |
+
|
| 73 |
+
base = AutoModelForCausalLM.from_pretrained(BASE, trust_remote_code=True, device_map="auto")
|
| 74 |
+
model = PeftModel.from_pretrained(base, ADAPTER)
|
| 75 |
+
|
| 76 |
+
# --- 推論の例(厳密JSONを狙うプロンプト) ---
|
| 77 |
+
obs = "turn | 3\nyour_active | Gholdengo\nopp_active | Great Tusk\nmoves | Make It Rain, Shadow Ball, Trick, Focus Blast"
|
| 78 |
+
# 例: allowed は内部で index に並べ替えた候補(move群→switch群)に対応
|
| 79 |
+
allowed = ["index::0","index::1","index::2","index::3"] # 例
|
| 80 |
+
prompt = (
|
| 81 |
+
"You are a Gen9 OU single-battle agent.\n"
|
| 82 |
+
"Return exactly one JSON object on a single line.\n"
|
| 83 |
+
'Schema: {"action": "index::<k>"} No markdown, no extra text.\n'
|
| 84 |
+
f"ALLOWED: {' | '.join(allowed)}\n\n"
|
| 85 |
+
f"{obs}\n\n"
|
| 86 |
+
"Action:"
|
| 87 |
+
)
|
| 88 |
+
|
| 89 |
+
inputs = tok(prompt, return_tensors="pt").to(model.device)
|
| 90 |
+
out_ids = model.generate(
|
| 91 |
+
**inputs,
|
| 92 |
+
max_new_tokens=48,
|
| 93 |
+
do_sample=False, # 温度0相当
|
| 94 |
+
eos_token_id=tok.eos_token_id,
|
| 95 |
+
pad_token_id=tok.eos_token_id
|
| 96 |
+
)
|
| 97 |
+
print(tok.decode(out_ids[0], skip_special_tokens=True))
|
| 98 |
+
````
|
| 99 |
+
|
| 100 |
+
> **Note:** MLX ランタイムで LoRA を直接ロードするには別途変換が必要です(標準の PEFT/Torch では上記のように動作します)。
|
| 101 |
|
| 102 |
+
---
|
| 103 |
|
| 104 |
## Training Details
|
| 105 |
|
| 106 |
### Training Data
|
| 107 |
|
| 108 |
+
* 出典: `jakegrigsby/metamon-parsed-replays`(Showdown リプレイの構造化アーカイブ)
|
| 109 |
+
* フィルタ: **Gen9 OU / Elo ≥ 1500** を中心に抽出・整形
|
| 110 |
+
* 生成された SFT データは以下の**index スキーマ**(簡略):
|
|
|
|
|
|
|
| 111 |
|
| 112 |
+
* `system`: 「厳密 JSON で 1 手のみ返す」等の指示
|
| 113 |
+
* `user`: `{ "state": {...}, "CANDIDATES": ["index::0", ...] }`
|
| 114 |
+
* `assistant`: `{ "action": "index::<k>" }`
|
| 115 |
|
| 116 |
+
### Preprocessing
|
| 117 |
|
| 118 |
+
* 候補(move / switch)を **アルファベット順**に整列し、`index::<k>` に対応付け。
|
| 119 |
+
* 観測は軽量テキスト(ターン/自他アクティブ/使用可能技の見出し名 etc.)に要約。
|
| 120 |
+
* 長さ上限(cutoff): 1024 tokens 目安。
|
| 121 |
|
| 122 |
+
### Training Procedure (LoRA / SFT)
|
| 123 |
|
| 124 |
+
* **PEFT LoRA:** `r=8, alpha=16, dropout=0.05, bias="none"`
|
| 125 |
+
**target\_modules:** `q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj`
|
| 126 |
+
* **Optimizer:** AdamW(`transformers.TrainingArguments(optim="adamw_torch")`)
|
| 127 |
+
* **LR:** 2e-4 近辺(スモーク→本学習でスケール)
|
| 128 |
+
* **Batch size:** 端末依存(例: `per_device_train_batch_size=8`, `gradient_accumulation_steps=1`)
|
| 129 |
+
* **Max steps:** データサイズに応じて設定(例: 10–25k)
|
| 130 |
+
* **Evaluation:** `eval_ratio ≈ 5%`, `eval_steps=500` 前後
|
| 131 |
+
`EarlyStoppingCallback(patience=3, metric=eval_loss)`
|
| 132 |
+
* **Precision:** fp32(Mac/MPS で安定運用)
|
| 133 |
|
| 134 |
+
> 実行スクリプトは TRL `SFTTrainer` を用いた標準的な SFT(packing 無効、`formatting_func` で chat template を適用)構成です。
|
| 135 |
|
| 136 |
+
---
|
|
|
|
|
|
|
|
|
|
|
|
|
| 137 |
|
| 138 |
## Evaluation
|
| 139 |
|
| 140 |
+
### Protocol
|
| 141 |
|
| 142 |
+
* **環境:** ローカル Pokémon Showdown (:8080), `poke-env` 経由
|
| 143 |
+
* **形式:** `gen9ou`(同一チーム同士で LLM vs Random の簡易ベースライン)
|
| 144 |
+
* **強制スキーマ:** 厳密 JSON 一個(`{"action": "index::<k>"}`)
|
| 145 |
|
| 146 |
+
### Result (example)
|
| 147 |
|
| 148 |
+
```
|
| 149 |
+
| Model | Backend | Format | Schema | Win% | Fallback% | Avg Lat(ms) | p95(ms) | Decis. | Battles |
|
| 150 |
+
|-----------------------------------------|---------|--------|--------|-----:|----------:|------------:|--------:|-------:|--------:|
|
| 151 |
+
| Qwen/Qwen3-1.7B + <this adapter> | hf | gen9ou | index | 80.0 | 0.0 | 1645.4 | 1728.6 | 346 | 10 |
|
| 152 |
+
```
|
| 153 |
|
| 154 |
+
* **補足:** 対戦相手は poke-env の `RandomPlayer`。本 LoRA の “index スキーマ厳守” と最小限観測だけで、安定した JSON 出力を確認。
|
| 155 |
+
* さらなる妥当性評価(他フォーマット、強い相手、別チーム、長期戦)や人手検証は今後の課題です。
|
| 156 |
|
| 157 |
+
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 158 |
|
| 159 |
+
## Bias, Risks, and Limitations
|
| 160 |
|
| 161 |
+
* 単手方策であり、**長期的なプランニングやリソース管理**は学習していません。
|
| 162 |
+
* **index スキーマ依存**のため、プロンプト逸脱や候補整列順の不一致で性能が大きく劣化します。
|
| 163 |
+
* データは公開リプレイ由来で、**プレイヤースキルやメタ**に偏りがあり得ます。
|
| 164 |
+
* ダメージ計算・乱数・特性相互作用は**簡略観測**のみで与えており、**完全再現ではありません**。
|
| 165 |
|
| 166 |
+
### Recommendations
|
| 167 |
|
| 168 |
+
* 生成の健全性チェック(JSON 解析、候補外出力のフォールバック)を必ず実装してください。
|
| 169 |
+
* 実運用では **評価対戦の拡充**(様々な構築・相手・ルール)を推奨します。
|
| 170 |
|
| 171 |
+
---
|
| 172 |
|
| 173 |
+
## Technical Specifications
|
| 174 |
|
| 175 |
+
### Architecture
|
| 176 |
|
| 177 |
+
* Qwen3-1.7B(Causal LM)+ LoRA(PEFT)
|
| 178 |
|
| 179 |
+
### Software
|
| 180 |
|
| 181 |
+
* Transformers / TRL / PEFT / PyTorch(MPS)
|
| 182 |
+
* Tokenizer は base に付属の chat template を使用(無い場合は簡易フォールバック)
|
| 183 |
|
| 184 |
+
---
|
| 185 |
|
| 186 |
+
## How to Cite / Credit
|
| 187 |
|
| 188 |
+
* Base: **Qwen/Qwen3-1.7B**
|
| 189 |
+
* Data inspiration: **metamon-parsed-replays**(Showdown 由来の公開リプレイ構造化)
|
| 190 |
|
| 191 |
+
---
|
| 192 |
|
| 193 |
+
## Model Card Authors
|
| 194 |
|
| 195 |
+
* 波浪 創(hellohazime) *
|
| 196 |
|
|
|
|
| 197 |
### Framework versions
|
| 198 |
|
| 199 |
+
* PEFT 0.17.1(動作確認)
|
| 200 |
+
* Transformers / TRL は 2025 時点の安定版で確認(詳細は `training_args.bin` を参照)
|