3.29k
The Ultra-Scale Playbook
🌌
The ultimate guide to training LLM on large GPU Clusters
d
-
-
Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme
Paper • 2504.02587 • Published • 32 -
RLHF Workflow: From Reward Modeling to Online RLHF
Paper • 2405.07863 • Published • 71 -
microsoft/Magma-8B
Image-Text-to-Text • 9B • Updated • 3.65k • 411