Skip to content
@OpenRLHF

OpenRLHF

Open-sourced Reinforcment Learning from Human Feedback

Pinned Loading

  1. OpenRLHF OpenRLHF Public

    An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)

    Python 8.4k 816

  2. OpenRLHF-M OpenRLHF-M Public

    An Easy-to-use, Scalable and High-performance RLHF Framework designed for Multimodal Models.

    Python 147 7

  3. OpenRLHF-Docs OpenRLHF-Docs Public

    3 4

Repositories

Showing 3 of 3 repositories
  • OpenRLHF Public

    An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)

    OpenRLHF/OpenRLHF’s past year of commit activity
    Python 8,427 Apache-2.0 816 282 21 Updated Nov 9, 2025
  • OpenRLHF-M Public

    An Easy-to-use, Scalable and High-performance RLHF Framework designed for Multimodal Models.

    OpenRLHF/OpenRLHF-M’s past year of commit activity
    Python 147 Apache-2.0 7 7 1 Updated Oct 6, 2025
  • OpenRLHF-Docs Public
    OpenRLHF/OpenRLHF-Docs’s past year of commit activity
    3 4 0 0 Updated Oct 5, 2025

Top languages

Python

Most used topics

Loading…