Papers › OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework

OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework

20 May 2024arXiv:2405.11143archive 2025-07-28

Jian Hu, Xibin Wu, Zilin Zhu, Xianyu, Weixun Wang, Dehao Zhang, Yu Cao

As large language models (LLMs) continue to grow by scaling laws, reinforcement learning from human feedback (RLHF) has gained significant attention due to its outstanding performance. However, unlike pretraining or fine-tuning a single model, scaling reinforcement learning from human feedback (RLHF) for training large language models poses coordination challenges across four models. We present OpenRLHF, an open-source framework enabling efficient RLHF scaling. Unlike existing RLHF frameworks that co-locate four models on the same GPUs, OpenRLHF re-designs scheduling for the models beyond 70B parameters using Ray, vLLM, and DeepSpeed, leveraging improved resource utilization and diverse training approaches. Integrating seamlessly with Hugging Face, OpenRLHF provides an out-of-the-box solution with optimized algorithms and launch scripts, which ensures user-friendliness. OpenRLHF implements RLHF, DPO, rejection sampling, and other alignment techniques. Empowering state-of-the-art LLM development, OpenRLHF's code is available at \url{https://github.com/OpenRLHF/OpenRLHF}.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

OpenLLMAI/OpenRLHF officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
openrlhf/openrlhf officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
OpenLLMAI/OpenLLaMA2 mentioned on GitHubpytorchApache-2.0 report
mickelliu/selfplay-redteaming mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Reinforcement LearningSchedulingreinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DPO

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections