mat-mul

mat-mul

kakaocorp

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 3 days ago

Let's Scale Step by Step: Compute-Efficient Hyperparameter Transfer for Large-Scale Mixture-of-Experts

updated a model 29 days ago

kakaocorp/kanana-2-30b-a3b-base

updated a model 29 days ago

kakaocorp/kanana-2-30b-a3b-instruct

View all activity

Organizations

upvoted a paper 3 days ago

Let's Scale Step by Step: Compute-Efficient Hyperparameter Transfer for Large-Scale Mixture-of-Experts

Paper • 2608.20061 • Published 6 days ago • 43

upvoted a collection about 2 months ago

Nemotron-Post-Training-v3

Collection of datasets used in the post-training phase of Nemotron Nano, Super, and Ultra v3. • 50 items • Updated 15 days ago • 197

upvoted a collection about 1 year ago

Kanana-1.5

Open Source Kanana-1.5 • 16 items • Updated Dec 1, 2025 • 29