RCEpic
eric-mitchell/direct-preference-optimization
Reference implementation for DPO (Direct Preference Optimization)
- Owner
- eric-mitchell (personal account)
- Stars
- Stars: 2,922
- Forks
- Forks: 235
- Language
- Python
- License
- Apache-2.0
- Created
- 2023
- Tier
- RC (2,000 to 4,999 ★) What this tier means
More repos by eric-mitchell
All 3 repos by eric-mitchell- eric-mitchell/detect-gptStars: 479PythonAlpha
- eric-mitchell/mendStars: 258PythonAlpha
Nearby in Python
All Python repos- kayak/pypikaStars: 2,923PythonRC
- facebookresearch/XLMStars: 2,922PythonRC
- keras-team/keras-tunerStars: 2,922PythonRC
- xflux-gui/fluxguiStars: 2,921PythonRC
- opencve/opencveStars: 2,921PythonRC