home/categories/llm-ai/cuba6112-skillfactory-skills-unsloth-grpo-skill-md
llm-aidata-ai

unsloth-grpo

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).

cuba6112
maintainer
cuba6112
آخر تحديث 12/26/2025
النجوم
0
التفرعات
0
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).

التثبيت
$ install --globalskills.sh
الاستخدام

بعد التثبيت، يمكنك استخدام هذه المهارة بتشغيل الأمر التالي في الطرفية:

skills use unsloth-grpo