home/categories/machine-learning/orchestra-research-ai-research-skills-06-post-training-grpo-rl-training-skill-md
machine-learningdata-ai
grpo-rl-training
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
maintainer
Orchestra-Research
更新於 11/20/2025
星標
6563
分支
515
quick start
Installation and usage
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
安裝
$ install --globalskills.sh
使用
安裝後,您可以通過在終端運行以下命令來使用此技能:
skills use grpo-rl-training