PrototypeCommon
liziniu/ReMax
Code for Paper (ReMax: A Simple, Efficient and Effective Reinforcement Learning Method for Aligning Large Language Models)
- Owner
- liziniu (personal account)
- Stars
- Stars: 200
- Forks
- Forks: 16
- Language
- Python
- License
- None
- Created
- 2023
- Topics
- large-language-modelsreinforcement-learningrlhfpolicy-gradient
- Tier
- Prototype (100 to 249 ★) What this tier means
Nearby in Python
All Python repos- OSINT-Experts-Society/Consensus-OSINTStars: 200PythonPrototype
- cdcailf/cjkfoldStars: 200PythonPrototype
- YoyoLin008/mcreplayStars: 200PythonPrototype
- aosp-mirror/tools_repoStars: 200PythonPrototype
- kfdm/gntpStars: 200PythonPrototype
- matthiask/plataStars: 200PythonPrototype