StableVery rare
OpenRLHF/OpenRLHF
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
- Owner
- OpenRLHF (organization)
- Stars
- Stars: 10,134
- Forks
- Forks: 1,052
- Language
- Python
- License
- Apache-2.0
- Created
- 2023
- Topics
- transformersvllmlarge-language-modelsraylibreinforcement-learning-from-human-feedbackreinforcement-learningproximal-policy-optimizationvisual-language-models
- Tier
- Stable (5,000 to 19,999 ★) What this tier means
More repos by OpenRLHF
All 2 repos by OpenRLHF- OpenRLHF/OpenRLHF-MStars: 163PythonPrototype
Nearby in Python
All Python repos- kyutai-labs/pocket-ttsStars: 10,162PythonStable
- Atarity/deploy-your-own-saasStars: 10,159PythonStable
- m87-labs/moondreamStars: 10,146PythonStable
- shmilylty/OneForAllStars: 10,129PythonStable
- drivendataorg/cookiecutter-data-scienceStars: 10,124PythonStable
- iam-veeramalla/Jenkins-Zero-To-HeroStars: 10,116PythonStable