home/categories/machine-learning/cuba6112-skillfactory-skills-unsloth-dpo-skill-md
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.

cuba6112
maintainer
cuba6112
更新日 12/26/2025
スター
0
フォーク
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.

インストール
$ install --globalskills.sh
使い方

インストール後、ターミナルで以下のコマンドを実行してこのスキルを使用できます:

skills use unsloth-dpo