lucidrains/MEGABYTE-pytorch

Implementation of MEGABYTE, Predicting Million-byte Sequences with Multiscale Transformers, in Pytorch

Training & fine-tuningPython MIT 55created 2023-05-15

Stars

658

1-day growth

7-day growth

—

30-day growth

—

Star history

Tracked since 2026-11-13

#artificial-intelligence#attention-mechanisms#deep-learning#learned-tokenization#long-context#transformers

Top contributors

Not collected yet (contributors job).

lucidrains/MEGABYTE-pytorch · AI Repo Stats