You're currently viewing an old version of this dataset. To see the current version, click here.

HH-RLHF

The HH-RLHF dataset is a human preference dataset for reinforcement learning from human feedback.

Data and Resources

Cite this as

Shusheng Xu, Wei Fu, Jiaxuan Gao, Wenjie Ye, Weilin Liu, Zhiyu Mei, Guangju Wang, Chao Yu, Yi Wu (2024). Dataset: HH-RLHF. https://doi.org/10.57702/xvs2nhsa

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2404.05530
Author Shusheng Xu
More Authors
Wei Fu
Jiaxuan Gao
Wenjie Ye
Weilin Liu
Zhiyu Mei
Guangju Wang
Chao Yu
Yi Wu
Homepage https://huggingface.co/OpenAssistant/oasst-rm-2-pythia-6.9b-epoch-1