home/categories/machine-learning/orchestra-research-ai-research-skills-06-post-training-slime-skill-md
machine-learningdata-ai
slime-rl-training
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.
maintainer
Orchestra-Research
更新日 1/29/2026
スター
6563
フォーク
515
quick start
Installation and usage
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.
インストール
$ install --globalskills.sh
使い方
インストール後、ターミナルで以下のコマンドを実行してこのスキルを使用できます：
skills use slime-rl-training