LeVanLoi'log, ⌚ 2025-02-18
***
Large Language Diffusion Models
Tác giả: [1]Renmin University of China, [2]Ant Group
Shen Nie1, Fengqi Zhu1, Zebin You1, Xiaolu Zhang2, Jingyang Ou1, Jun Hu2, Jun Zhou2, Yankai Lin1, Ji-Rong Wen1, Chongxuan Li1
~
We introduce LLaDA, a diffusion model with an unprecedented 8B scale, trained entirely from scratch, rivaling LLaMA3 8B in performance.