PJMixers/mlabonne_orpo-dpo-mix-40k-PreferenceShareGPT
收藏官方服务：
资源简介：
--- tags: - preference - preferences size_categories: - 10K<n<100K task_categories: - reinforcement-learning ---
This dataset contains information related to user preferences or choices, suitable for reinforcement learning tasks, with a size between 10,000 and 100,000 records.
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
- 10K<n<100K
任务分类
- 强化学习
