Skip to content

An Easy-to-use, Scalable and High-performance RLHF Framework (Support 70B+ full tuning & LoRA & Mixtral & KTO)

License

Notifications You must be signed in to change notification settings

mickelliu/OpenRLHF

 
 

Repository files navigation

OpenRLHF (forked)

A fork made specific changes to be ran on AI2 beaker and UW Hyak clusters. Please check out the original repo documentations and supports.

Citation

@misc{hu23openrlhf,
   author = {Jian Hu and Xibin Wu and Xianyu and Chen Su and Leon Qiu and Daoning Jiang and Qing Wang and Weixun Wang},
   title = {OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework},
   year={2023},
   publisher = {GitHub},
   journal = {GitHub repository},
   howpublished = {\url{https://github.com/OpenLLMAI/OpenRLHF}}
}

OpenRLHF © 2024 OpenLLMAI. All Rights Reserved.

About

An Easy-to-use, Scalable and High-performance RLHF Framework (Support 70B+ full tuning & LoRA & Mixtral & KTO)

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 99.0%
  • Other 1.0%