computational-chemistryresearch
unsloth-orpo
One-step preference alignment using Odds Ratio Preference Optimization (ORPO) (triggers: ORPO, preference optimization, alignment, ORPOTrainer, log_odds_ratio, binary preference).
maintainer
cuba6112
更新於 12/26/2025
星標
0
分支
0
quick start
Installation and usage
One-step preference alignment using Odds Ratio Preference Optimization (ORPO) (triggers: ORPO, preference optimization, alignment, ORPOTrainer, log_odds_ratio, binary preference).
安裝
$ install --globalskills.sh
使用
安裝後，您可以透過在終端機執行以下指令來使用此技能：
skills use unsloth-orpo