MEGABYTE-pytorch
PublicImplementation of MEGABYTE, Predicting Million-byte Sequences with Multiscale Transformers, in Pytorch
artificial-intelligenceattention-mechanismsdeep-learninglearned-tokenizationlong-contexttransformers
Creat:2023-05-15T11:27:36
Update:2025-03-16T11:08:31
647
Stars
0
Stars Increase