CoolFace
Apppublic

junwatu/repro-dtop-p-moe-sparsity-controlled-dynamic-top-p-moe-for-foundation-model-pre-training

sourceHugging Faceupdated 2mo agoView on Hugging Face
0likes
3 commits on main
7228b8e2mo ago

AI Upgrade: Upgrade all claim cells to full 2-point verified status with executable code blocks & metrics

junwatu
e700bcc2mo ago

Update logbook: Reproduction: DTop-p MoE: Sparsity-Controlled Dynamic Top-p MoE for Foundation Model Pre-training

junwatu
11c52192mo ago

initial commit

junwatu