ByT5: Towards a token-free future with pre-trained byte-to-byte models

Code

• github.com/google-research/byt5
  OfficialIn papertf★ 539
• github.com/ufal/multilexnorm2021
  pytorch★ 16
• github.com/yoreG123/Paddle-ByT5
  paddle★ 2
• github.com/2024-MindSpore-1/Code2/tree/main/model-1/byt5
  mindspore★ 0
• github.com/huggingface/transformers/tree/master/src/transformers/models/byt5
  jax★ 0

Abstract

Most widely-used pre-trained language models operate on sequences of tokens corresponding to word or subword units. By comparison, token-free models that operate directly on raw text (bytes or characters) have many benefits: they can process text in any language out of the box, they are more robust to noise, and they minimize technical debt by removing complex and error-prone text preprocessing pipelines. Since byte or character sequences are longer than token sequences, past work on token-free models has often introduced new model architectures designed to amortize the cost of operating directly on raw text. In this paper, we show that a standard Transformer architecture can be used with minimal modifications to process byte sequences. We characterize the trade-offs in terms of parameter count, training FLOPs, and inference speed, and show that byte-level models are competitive with their token-level counterparts. We also demonstrate that byte-level models are significantly more robust to noise and perform better on tasks that are sensitive to spelling and pronunciation. As part of our contribution, we release a new set of pre-trained byte-level Transformer models based on the T5 architecture, as well as all code and data used in our experiments.

Tasks

Benchmark Results

Reproductions