PrototypeCommon
xrsrke/instructGOOSE
Implementation of Reinforcement Learning from Human Feedback (RLHF)
- Owner
- xrsrke (personal account)
- Stars
- Stars: 173
- Forks
- Forks: 21
- Language
- Jupyter Notebook
- License
- MIT
- Created
- 2022
- Topics
- instructgptreinforcement-learningrlhfchatgpthuman-feedback
- Tier
- Prototype (100 to 249 ★) What this tier means
More repos by xrsrke
All 2 repos by xrsrke- xrsrke/toolformerStars: 145Jupyter NotebookPrototype
Nearby in Jupyter Notebook
All Jupyter Notebook repos- alexeygrigorev/workshopsStars: 173Jupyter NotebookPrototype
- InternScience/scpStars: 173Jupyter NotebookPrototype
- VizuaraAILabs/DeepSeek-From-ScratchStars: 173Jupyter NotebookPrototype
- ContinuumIO/numbapro-examplesStars: 173Jupyter NotebookPrototype
- microsoft/Cognitive-Vision-PythonStars: 173Jupyter NotebookPrototype
- eleanorlutz/AnimatedPythonPatternsStars: 173Jupyter NotebookPrototype