Cerebras REAP Collection Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 19 items • Updated 10 days ago • 70
REAP the Experts: Why Pruning Prevails for One-Shot MoE compression Paper • 2510.13999 • Published Oct 15 • 6
The Dragon Hatchling: The Missing Link between the Transformer and Models of the Brain Paper • 2509.26507 • Published Sep 30 • 537