AlphaUncommon
uclaml/SPPO
The official implementation of Self-Play Preference Optimization (SPPO)
- Owner
- uclaml (personal account)
- Stars
- Stars: 590
- Forks
- Forks: 48
- Language
- Python
- License
- Apache-2.0
- Created
- 2024
- Topics
- deep-learningfine-tuninglarge-language-modelsrlhfself-play
- Tier
- Alpha (250 to 699 ★) What this tier means
More repos by uclaml
All 3 repos by uclaml- uclaml/SPINStars: 1,255PythonBeta
- uclaml/Rephrase-and-RespondStars: 104PythonPrototype
Nearby in Python
All Python repos- eliasswu/AlphaPurifyStars: 590PythonAlpha
- TX-Leo/HumanEgoStars: 590PythonAlpha
- dob323/session-kitStars: 590PythonAlpha
- jbernard/dotfilesStars: 590PythonAlpha
- syrusakbary/validate_emailStars: 590PythonAlpha
- oeddyo/algorithmStars: 590PythonAlpha