Downloads · 30 days
21
2% of all-time downloads
dpo-qwen-cot-merged
SumiYama/dpo-qwen-cot-merged
dpo-qwen-cot-merged is a machine learning model from SumiYama. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
- ベースモデル: Qwen/Qwen3-4B-Instruct-2507 - 学習手法: LoRA SFT → マージ - LoRA設定: r=16, alpha=32 - 対象タスク: DBBench (SQL), ALFWorld (家事タスク)
All-time downloads
1.1K
Public
Parameters
4B
88.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors16.1 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Feb 4, 2026
- Updated
- Feb 14, 2026
- SHA
- 6eba47b3
Base models
Model card
From the Hugging Face model README
AgentBench SFT Model
モデル概要
- ベースモデル: Qwen/Qwen3-4B-Instruct-2507
- 学習手法: LoRA SFT → マージ
- LoRA設定: r=16, alpha=32
- 対象タスク: DB_Bench (SQL), ALFWorld (家事タスク)
推論方法 (vLLM)
docker run --runtime nvidia --gpus all \
--ipc=host \
vllm/vllm-openai:0.13.0 \
--model SumiYama/dpo-qwen-cot-merged \
--max-model-len 8192 \
--gpu-memory-utilization 0.95
学習データ
- DB_Bench形式の合成SQLエージェント対話
- ALFWorld形式の合成家事タスク対話
- AgentBenchのデータは使用していません
- Type
- qwen3
- License
- apache-2.0
- Created
- Feb 4, 2026
- Updated
- Feb 14, 2026