OpenRLHF Files

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

This is an exact mirror of the OpenRLHF project, hosted at https://github.com/OpenRLHF/OpenRLHF. SourceForge is not affiliated with OpenRLHF. For more information, see the SourceForge Open Source Mirror Directory.

The interactive file manager requires Javascript. Please enable it or use sftp or scp.
You may still browse the files here.

Name	Modified	Size	InfoDownloads / Week
Parent folder
README.md	2025-09-22	1.2 kB	0
Release v0.8.11 source code.tar.gz	2025-09-22	372.1 kB	0
Release v0.8.11 source code.zip	2025-09-22	458.0 kB	0
Totals: 3 Items		831.3 kB	0

What's Changed

Fix PPO progress display when resuming from a checkpoint by @zhaoxu98 in https://github.com/OpenRLHF/OpenRLHF/pull/1124
Add --tokenizer_chat_template argument to the DPO trainer by @armsp in https://github.com/OpenRLHF/OpenRLHF/pull/1129
Add GEM: A Gym for Generalist LLMs demo by @xiaoxigua999 in https://github.com/OpenRLHF/OpenRLHF/commit/4e9a12f9f902db880d4a599e18b36ab37c7742d4
Bump vLLM to 0.10.2 by @xiaoxigua999 in https://github.com/OpenRLHF/OpenRLHF/commit/b678e303a3d432b271b85527365ab4cd2467f9b7
Bump DeepSpeed to 0.17.6 by @xiaoxigua999 in https://github.com/OpenRLHF/OpenRLHF/commit/ac3689ece2666cb524836568b88bfc6016dabc6f
Bump Transformers to 4.56.1 by @xiaoxigua999 in https://github.com/OpenRLHF/OpenRLHF/commit/564e4672dee0f1599c2dfe434f135a8c9570318f

New Contributors

@zhaoxu98 made their first contribution in https://github.com/OpenRLHF/OpenRLHF/pull/1124
@armsp made their first contribution in https://github.com/OpenRLHF/OpenRLHF/pull/1129

Full Changelog: https://github.com/OpenRLHF/OpenRLHF/compare/v0.8.10...v0.8.11

Source: README.md, updated 2025-09-22

Other Useful Business Software

Auth0 for AI Agents now in GA Icon

Auth0 for AI Agents now in GA

Ready to implement AI with confidence (without sacrificing security)?

Connect your AI agents to apps and data more securely, give users control over the actions AI agents can perform and the data they can access, and enable human confirmation for critical agent actions.

Start building today

Orchestrate Your AI Agents with Zenflow Icon

Orchestrate Your AI Agents with Zenflow

The multi-agent workflow engine for modern teams. Zenflow executes coding, testing, and verification with deep repo awareness

Zenflow orchestrates AI agents like a real engineering system. With parallel execution, spec-driven workflows, and deep multi-repo understanding, agents plan, implement, test, and verify end-to-end. Upgrade to AI workflows that work the way your team does.

Try free now

Recommended Projects

Ray
A unified framework for scalable computing
PMIAS
Agents based reinforcement learning using Mathematica
Gymnasium
An API standard for single-agent reinforcement learning environments
SkyAI
Highly modularized Reinforcement Learning library for real/simulation robots to learn behaviors. Our ultimate goal is to develop an artificial intelligence (AI) program with which the robots can learn to behave as their users wish.
ViZDoom
Doom-based AI research platform for reinforcement learning