machine-learningdata-ai
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.
maintainer
math-inc
Обновлено 3/19/2026
Звёзды
1165
Форки
96
quick start
Installation and usage
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.
Установка
$ install --globalskills.sh
Использование
После установки вы можете использовать этот skill, выполнив следующую команду в терминале:
skills use simpo-training