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
์
๋ฐ์ดํธ๋จ 12/26/2025
์คํ
0
ํฌํฌ
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).
์ค์น
$ install --globalskills.sh
์ฌ์ฉ๋ฒ
์ค์น ํ ํฐ๋ฏธ๋์์ ๋ค์ ๋ช ๋ น์ ์คํํ์ฌ ์ด ์คํฌ์ ์ฌ์ฉํ ์ ์์ต๋๋ค:
skills use unsloth-orpo