PJMixers/PKU-Alignment_PKU-SafeRLHF-Safer-PreferenceShareGPT
收藏数据链接：
官方服务：
资源简介：
--- tags: - preference - preferences size_categories: - 100K<n<1M task_categories: - reinforcement-learning ---
This dataset contains information related to preferences, with a sample size between 100K and 1M, suitable for reinforcement learning tasks.
提供机构：
PJMixers原始信息汇总
数据集标签
- 偏好
- 偏好
数据集大小分类
- 100K<n<1M
任务分类
- 强化学习
