princeton-nlp/SimPO

[NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward

LLM & foundation modelsPython MIT 77created 2024-05-21

Stars

964

1-day growth

7-day growth

—

30-day growth

—

Star history

Tracked since 2026-11-13

#alignment#large-language-models#preference-alignment#rlhf

Top contributors

Not collected yet (contributors job).

princeton-nlp/SimPO · AI Repo Stats