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
Обновлено 12/26/2025
Звёзды
0
Форки
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).

Установка
$ install --globalskills.sh
Использование

После установки вы можете использовать этот skill, выполнив следующую команду в терминале:

skills use unsloth-grpo