Skip to content

benchang1110

Qwen2.5-Taiwan-3B-Reason-GRPO

benchang1110/Qwen2.5-Taiwan-3B-Reason-GRPO

Qwen2.5-Taiwan-3B-Reason-GRPO is a text generation model from benchang1110. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.

此模型微調自 benchang1110/Qwen2.5-Taiwan-3B-Reason-SFT (基於阿里巴巴千問)。 由 GRPO 方法訓練,資料集為 benchang1110/Big-Math-RL-Verified-zhtw,僅採用 solve rate 大於 0.7 的題目作為訓練。

Downloads · 30 days

18

10% of all-time downloads

All-time downloads

188

Public

Parameters

3.4B

6.8 GB on disk

Likes

1

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors6.8 GB · 100%

At a glance

Task
Text Generation
Library
transformers
License
other
Model type
qwen2
Access
Public
Created
Apr 25, 2025
Updated
Apr 27, 2025
SHA
c6ebeeb4

Base models

Task
Text Generation
Library
transformers
Type
qwen2
License
other
Languages
zh
Created
Apr 25, 2025
Updated
Apr 27, 2025