machine-learningdata-ai
unsloth-dpo
Direct Preference Optimization (DPO) for aligning models with preference data without separate reward models. Triggers: dpo, preference optimization, rlhf, ref_model=none, patchdpotrainer, dpotrainer.
maintainer
cuba6112
업데이트됨 12/26/2025
스타
0
포크
0
quick start
Installation and usage
Direct Preference Optimization (DPO) for aligning models with preference data without separate reward models. Triggers: dpo, preference optimization, rlhf, ref_model=none, patchdpotrainer, dpotrainer.
설치
$ install --globalskills.sh
사용법
설치 후 터미널에서 다음 명령을 실행하여 이 스킬을 사용할 수 있습니다:
skills use unsloth-dpo