quick start
Installation and usage
Implementation of Group Relative Policy Optimization (GRPO) for training reasoning models, optimized for 8x memory savings (triggers: GRPO, reasoning, DeepSeek-R1, reinforcement learning, RLVR, GRPOTrainer, thinking tokens).
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 unsloth-grpo