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.

synthetic-sciences Updated 4.4k repo stars
An OpenScience session comparing EGFR inhibitor potency: the trace shows the search, the written files, the analysis run and the answer with a results table

File contents

synthetic-sciences/openscience commit c5bb062bb4

Frequently asked questions

npx get-skill add synthetic-sciences/simpo-training