Simpo Reference Free Preference Optimization

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

robertoatila Updated 9 repo stars
J.A.R.V.I.S. — Autonomous Cognitive Runtime

File contents

robertoatila/jarvis-skill-registry commit 83aca2b8d8

Frequently asked questions

npx get-skill add robertoatila/simpo-reference-free-preference-optimization-2