BetaRare
princeton-nlp/SimPO
[NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward
- Owner
- princeton-nlp (organization)
- Stars
- Stars: 963
- Forks
- Forks: 77
- Language
- Python
- License
- MIT
- Created
- 2024
- Topics
- alignmentlarge-language-modelspreference-alignmentrlhf
- Tier
- Beta (700 to 1,999 ★) What this tier means
More repos by princeton-nlp
All 28 repos by princeton-nlp- princeton-nlp/tree-of-thought-llmStars: 6,087PythonStable
- princeton-nlp/SimCSEStars: 3,658PythonRC
- princeton-nlp/MeZOStars: 1,182PythonBeta
- princeton-nlp/PUREStars: 814PythonBeta
- princeton-nlp/LM-BFFStars: 727PythonBeta
- princeton-nlp/LLM-ShearingStars: 643PythonAlpha
Nearby in Python
All Python repos- Kuaishou-OneRec/OpenOneRecStars: 963PythonBeta
- voicecomm-ai/ai-vocsagex-backendStars: 963PythonBeta
- cayu-dev/cayuStars: 963PythonBeta
- nilmtk/nilmtkStars: 963PythonBeta
- gsoc-cn/gsoc-cnStars: 963PythonBeta
- toadstorm/MOPSStars: 963PythonBeta