home/categories/machine-learning/atrawog-bazzite-ai-plugins-bazzite-ai-jupyter-skills-reward-skill-md
machine-learningdata-ai
reward
Reward model training for RLHF pipelines. Covers RewardTrainer, preference dataset preparation, sequence classification heads, and reward scaling for stable reinforcement learning. Includes thinking quality scoring patterns.
maintainer
atrawog
更新日 1/12/2026
スター
0
フォーク
0
quick start
Installation and usage
Reward model training for RLHF pipelines. Covers RewardTrainer, preference dataset preparation, sequence classification heads, and reward scaling for stable reinforcement learning. Includes thinking quality scoring patterns.
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 reward