Gen-Verse/ReasonFlux-V2-Reasoner-DPO
收藏Hugging Face2025-08-07 更新2025-07-05 收录
下载链接：
https://hf-mirror.com/datasets/Gen-Verse/ReasonFlux-V2-Reasoner-DPO
下载链接
链接失效反馈官方服务：
资源简介：
这是一个用于Template Reasoner模块的DPO数据集，用于在ReasonFlux-V2推理范式中进行训练。数据集包含了根据问题提出的思维模板，以及Template Reasoner模块根据这些模板进行精确推理所需的数据。
This is the DPO dataset for the Template Reasoner module, used for training in the ReasonFlux-V2 reasoning paradigm. The dataset includes thought templates proposed based on problems, and the data required for the Template Reasoner module to perform precise reasoning following these templates.
提供机构：
Gen-Verse
