Sweaterdog/Smol-reason2.1-base
收藏Hugging Face2025-04-05 更新2025-04-12 收录
下载链接：
https://hf-mirror.com/datasets/Sweaterdog/Smol-reason2.1-base
下载链接
链接失效反馈官方服务：
资源简介：
Smol-reason2.1数据集包含了许多来自Open-R1数据集中的数学和编程相关示例，用于对Smol-reason2.1模型进行PPO步骤的微调。
This dataset includes tons of examples from Open-R1s datasets regarding math, and coding, this will be used as the PPO step of fine tuning Smol-reason2.1.
提供机构：
Sweaterdog
