Back to List
Notice:This resource is provided by a third-party author. Please review the code with AI tools or manually before use to ensure security and compatibility.
PythonOpenRLHF/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)

85.5/100
9.8KForks: 988
View on GitHubHomepage →
Loading report...

Similar Projects

ml-engineering

77

Machine Learning Engineering Open Book

Python18.5K

train-llm-from-scratch

71

A straightforward method for training your LLM, from downloading data to generating text.

Python8.6K

PaLM-rlhf-pytorch

74

Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

Python7.9K

LLM-RL-Visualized

72

🌟100+ 原创 LLM / RL 原理图📚,《大模型算法》作者巨献!💥(100+ LLM/RL Algorithm Maps )

Python4.7K
Back to List