Papers
arxiv:2405.11143

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

Published on May 20
ยท Submitted by akhaliq on May 21
#3 Paper of the day

Abstract

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 https://github.com/OpenLLMAI/OpenRLHF.

Community

It's awesome that it's compatible with models on the hub๐Ÿ”ฅ

Unlocking RLHF: The Power of OpenRLHF for Large Language Models

Links ๐Ÿ”—:

๐Ÿ‘‰ Subscribe: https://www.youtube.com/@Arxflix
๐Ÿ‘‰ Twitter: https://x.com/arxflix
๐Ÿ‘‰ LMNT (Partner): https://lmnt.com/

By Arxflix
9t4iCUHx_400x400-1.jpg

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2405.11143 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2405.11143 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2405.11143 in a Space README.md to link it from this page.

Collections including this paper 21