PJMixers/M4-ai_prm_dpo_pairs_cleaned-PreferenceShareGPT
收藏Hugging Face2024-05-30 更新2024-06-15 收录
下载链接：
https://hf-mirror.com/datasets/PJMixers/M4-ai_prm_dpo_pairs_cleaned-PreferenceShareGPT
下载链接
链接失效反馈官方服务：
资源简介：
---
tags:
- preference
- preferences
size_categories:
- 1K<n<10K
task_categories:
- reinforcement-learning
---
This dataset pertains to user preferences or choices, containing between 1 thousand and 10 thousand data points, and is 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
- 1K<n<10K
任务分类
- 强化学习
