Skip to content

xinyuran

Qwen2.5-7B-RLRefine

xinyuran/Qwen2.5-7B-RLRefine

Qwen2.5-7B-RLRefine is a text generation model from xinyuran. Use it when you need the model to write or continue text. The card lists the license as mit.

基于 SFT → DPO → GRPO 三阶段 RL 训练的中文电商评论关键词提取模型

Downloads · 30 days

11

5% of all-time downloads

All-time downloads

241

Public

Parameters

7.6B

15.2 GB on disk

Likes

0

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors15.2 GB · 100%

At a glance

Task
Text Generation
License
mit
Model type
qwen2
Access
Public
Created
May 9, 2026
Updated
May 11, 2026
SHA
bd15e8e0

Base models

Task
Text Generation
Type
qwen2
License
mit
Languages
zh
Created
May 9, 2026
Updated
May 11, 2026