teamcore/DPO_Pm3B_RMAB_TG_clean_beta0.25dpo_proEurus_RM_7b_nu0.003_CR_cr_trajfull
收藏数据链接：
官方服务：
资源简介：
该数据集包含三个字段：提示(prompt)、选择(chosen)和回应(response)，均为文本格式。它被划分为一个默认的部分，共有1200个示例，总大小约为10MB。提供的配置为默认配置，包含了数据文件的路径信息。
The dataset includes three fields: prompt, chosen, and response, all in string format. It is divided into a default split with a total of 1200 examples, approximately 10MB in size. The provided configuration is the default one, which includes the path to the data files.
提供机构：
teamcore
