PJMixers/neovalle_H4rmony_dpo-PreferenceShareGPT
收藏官方服务：
资源简介：
--- task_categories: - reinforcement-learning tags: - preference - preferences size_categories: - 1K<n<10K ---
This dataset is primarily used for reinforcement learning tasks, involving tags related to preference and preferences, with a size between 1,000 and 10,000 samples.
提供机构：
PJMixers原始信息汇总
数据集概述
任务类别
- 强化学习
标签
- 偏好
- 偏好
数据规模
- 1K<n<10K
