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
Обновлено 11/20/2025
Звёзды
6563
Форки
515
quick start
Installation and usage
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
Установка
$ install --globalskills.sh
Использование
После установки вы можете использовать этот skill, выполнив следующую команду в терминале:
skills use grpo-rl-training