machine-learningdata-ai
dpo
Direct Preference Optimization for learning from preference pairs. Covers DPOTrainer, preference dataset preparation, implicit reward modeling, and beta tuning for stable preference learning without explicit reward models. Includes thinking quality patterns.
maintainer
atrawog
更新于 1/12/2026
星标
0
分支
0
quick start
Installation and usage
Direct Preference Optimization for learning from preference pairs. Covers DPOTrainer, preference dataset preparation, implicit reward modeling, and beta tuning for stable preference learning without explicit reward models. Includes thinking quality patterns.
安装
$ install --globalskills.sh
使用
安装后，您可以通过在终端运行以下命令来使用此技能：
skills use dpo