Claude
Code & Development
Trust: 55/100 (Fair)simpo-training Guide
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.
8,991 starsby zechenzhangagi
When to use 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.
How to use simpo-training
simpo-training is a Claude skill in the SKILL.md format. Add it to your Claude environment from the source repository below, then it activates as a user-invocable skill when your task matches its description.
Details
PlatformClaude
CategoryCode & Development
Invocationuser-invocable
Modelany
Maintainerzechenzhangagi
LicenseMIT