teamcore/DPO_Pm3B_RMAB_TG_clean_beta0.25dpo_proEurus_RM_7b
收藏Hugging Face2025-11-07 更新2025-11-15 收录
下载链接：
https://hf-mirror.com/datasets/teamcore/DPO_Pm3B_RMAB_TG_clean_beta0.25dpo_proEurus_RM_7b
下载链接
链接失效反馈官方服务：
资源简介：
该数据集名为CR，包含了多个字段，如任务类型、选择、拒绝等。数据集分为默认划分，共包含2000个示例。具体的应用场景和详细描述在README中未提及。
The dataset is named CR, containing multiple fields such as task type, chosen, rejected, etc. The dataset is split into a default division with a total of 2000 examples. The specific application scenario and detailed description are not mentioned in the README.
提供机构：
teamcore
