Skip to main content

ai-research-06-post-training-slime

Guides LLM post-training with RL using the slime framework, integrating Megatron-LM for efficient model training and data generation.

Install this skill

or
ai-research-06-post-training-slime3 files

Comments

Sign in to leave a comment.

No comments yet. Be the first to comment!
Installation guide →