YuchenLi01/Math-Step-DPO-10K-augmented-Qwen2.5MathRM72B
收藏Hugging Face2025-04-09 更新2025-04-12 收录
下载链接：
https://hf-mirror.com/datasets/YuchenLi01/Math-Step-DPO-10K-augmented-Qwen2.5MathRM72B
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含了多个文本字段和分数字段，用于记录关于某个任务的不同步骤和选项的详细信息，以及对应的分数。数据集分为训练集，提供了相应的文件路径。
The dataset includes multiple text fields and score fields, recording detailed information about different steps and options for a certain task, as well as the corresponding scores. The dataset is split into a training set and provides the corresponding file paths.
提供机构：
YuchenLi01
