PrototypeCommon
tomekkorbak/pretraining-with-human-feedback
Code accompanying the paper Pretraining Language Models with Human Preferences
- Owner
- tomekkorbak (personal account)
- Stars
- Stars: 185
- Forks
- Forks: 16
- Language
- Python
- License
- MIT
- Created
- 2023
- Topics
- ai-alignmentai-safetydecision-transformersgptlanguage-modelspretrainingreinforcement-learningrlhf
- Tier
- Prototype (100 to 249 ★) What this tier means
Nearby in Python
All Python repos- MarionLepert/opendermStars: 185PythonPrototype
- preferencemodel/karotteStars: 185PythonPrototype
- nutllwhy/code-brand-filmStars: 185PythonPrototype
- sourcepole/qgis-openlayers-pluginStars: 185PythonPrototype
- petewarden/geodictStars: 185PythonPrototype
- Jajcus/pyxmpp2Stars: 185PythonPrototype