2 results found Sort:

lucidrains
MEGABYTE-pytorch lucidrains
53
634
mit
10
Implementation of MEGABYTE, Predicting Million-byte Sequences with Multiscale Transformers, in Pytorch
long-context transformers deep-learning attention-mechanisms learned-tokenization artificial-intelligence
Created 2023-05-15
36 commits to main branch, last one about a month ago
lucidrains
rvq-vae-gpt lucidrains
1
83
mit
4
My attempts at applying Soundstream design on learned tokenization of text and then applying hierarchical attention to text generation
gpt deep-learning text-autoencoder learned-tokenization artificial-intelligence
Created 2023-01-30
30 commits to main branch, last one 3 months ago