Simpo Training

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.

photonics-dhl Updated 0 repo stars

File contents

photonics-dhl/scholar-s-tea commit 814c185274

Frequently asked questions

npx get-skill add photonics-dhl/simpo-training