1231czx/7B_iter3_dpo_N1_random_pair_onpolicy_only
收藏Hugging Face2024-07-01 更新2024-07-06 收录
下载链接：
https://hf-mirror.com/datasets/1231czx/7B_iter3_dpo_N1_random_pair_onpolicy_only
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含多个特征，包括gt（字符串类型）、rej（字符串序列）、chosen（包含content和role的列表）和rejected（同样包含content和role的列表）。数据集分为一个训练集，包含16371个样本，总大小为35108968字节。下载大小为13996274字节。
The dataset includes multiple features such as gt (string type), rej (sequence of strings), chosen (a list containing content and role), and rejected (also a list containing content and role). The dataset is divided into a training set with 16,371 samples, totaling 35,108,968 bytes. The download size is 13,996,274 bytes.
提供机构：
1231czx
