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
this https URL

大型语言模型的尺寸不断增加，其卓越性能使得基于人类反馈的强化学习备受关注。本文提出了一个名为 OpenRLHF 的开源框架，通过使用 Ray、vLLM 和 DeepSpeed 重新设计对四个模型的调度以实现对超过 70B 参数的大型语言模型进行有效的强化学习训练。OpenRLHF 与 Hugging Face 无缝集成，并提供了优化的算法和启动脚本，确保用户友好性。