PrototypeCommon
vwxyzjn/lm-human-preference-details
RLHF implementation details of OAI's 2019 codebase
- Owner
- vwxyzjn (personal account)
- Stars
- Stars: 200
- Forks
- Forks: 12
- Language
- Python
- License
- MIT
- Created
- 2023
- Tier
- Prototype (100 to 249 ★) What this tier means
More repos by vwxyzjn
All 7 repos by vwxyzjn- vwxyzjn/cleanrlStars: 10,634PythonStable
- vwxyzjn/ppo-implementation-detailsStars: 963PythonBeta
- vwxyzjn/portwardenStars: 637GoAlpha
- vwxyzjn/invalid-action-maskingStars: 171PythonPrototype
- vwxyzjn/summarize_from_feedback_detailsStars: 165PythonPrototype
- vwxyzjn/cleanbaStars: 127PythonPrototype
Nearby in Python
All Python repos- fendouai/awesome-embodied-aiStars: 200PythonPrototype
- YoyoLin008/mcreplayStars: 200PythonPrototype
- TomAnthony/YourOwnWeighStars: 200PythonPrototype
- aosp-mirror/tools_repoStars: 200PythonPrototype
- kfdm/gntpStars: 200PythonPrototype
- matthiask/plataStars: 200PythonPrototype