MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers

Part of Advances in Neural Information Processing Systems 36 (NeurIPS 2023) Main Conference Track

Bibtex Paper Supplemental


LILI YU, Daniel Simig, Colin Flaherty, Armen Aghajanyan, Luke Zettlemoyer, Mike Lewis


Autoregressive transformers are spectacular models for short sequences but scale poorly to long sequences such as high-resolution images, podcasts, code, or books. We proposed Megabyte, a multi-scale decoder architecture that enables end-to-end differentiable modeling of sequences of over one million bytes. Megabyte segments sequences into patches and uses a local submodel within patches and a global model between patches. This enables sub-quadratic self-attention, much larger feedforward layers for the same compute, and improved parallelism during decoding---unlocking better performance at reduced cost for both training and generation. Extensive experiments show that Megabyte allows byte-level models to perform competitively with subword models on long context language modeling, achieve state-of-the-art density estimation on ImageNet, and model audio from raw files. Together, these results establish the viability of tokenization-free autoregressive sequence modeling at scale.