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

Related tags

Text Data & NLPbyt5
Overview

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

ByT5 is a tokenizer-free extension of the mT5 model. Instead of using a subword vocabulary like most other pretrained language models (BERT, XLM-R, T5, GPT-3), our ByT5 model operates directly on UTF-8 bytes, removing the need for any text preprocessing. Beyond the reduction in system complexity, we find that parameter-matched ByT5 models are competitive with mT5 across a range of tasks, and outperform mT5 on tasks that involve noisy text or are sensitive to spelling and pronunciation. This repo can be used to reproduce the experiments in the ByT5 paper.

Usage

Training

To run this code, you need to install the t5 library. General instructions for training, fine-tuning, evaluation, and exporting models for inference can be found in the t5 repo. In order to use the additional ByT5 tasks provided in this library with the t5_mesh_transformer command, run from this directory and add the flag --module_import="byt5.tasks".

To train a ByT5-Large model on the mc4 task from scratch as described in the paper:

export PROJECT=yourproject
export ZONE=yourzone
export BUCKET=yourbucket
export TPU=yourtpu

ctpu up --name=$TPU --project=$PROJECT --zone=$ZONE --tpu-size=v3-256 --tpu-only --noconf

TASK=byt5_mc4
MODEL_DIR="${BUCKET}${TASK}"

python -m t5.models.mesh_transformer_main \
  --tpu="${TPU}" \
  --gcp_project="${PROJECT}" \
  --tpu_zone="${ZONE}" \
  --model_dir="${MODEL_DIR}" \
  --gin_file="models/byt5.large.gin" \
  --gin_param="MIXTURE_NAME = '${TASK}'" \
  --gin_param="utils.run.sequence_length = {'inputs': 1024, 'targets': 189}" \
  --gin_param="utils.run.batch_size = ('tokens_per_batch', 1048576)" \
  --gin_param="[email protected]_rate_schedules.rsqrt_no_ramp_down" \
  --gin_param="run.train_steps = 1000000" \
  --gin_param="utils.tpu_mesh_shape.model_parallelism = 1" \
  --gin_param="utils.tpu_mesh_shape.tpu_topology = 'v3-256'" \
  --eval_mode="perplexity_eval" \
  --eval_gin_param="mesh_eval_dataset_fn.num_eval_examples = 10000" \
  --t5_tfds_data_dir="${BUCKET}/t5-tfds" \
  --module_import="byt5.tasks"

Fine-Tuning

The example below shows how to finetune the ByT5-Large model on the XNLI zeroshot task.

export PROJECT=yourproject
export ZONE=yourzone
export BUCKET=yourbucket
export TPU=yourtpu

ctpu up --name=$TPU --project=$PROJECT --zone=$ZONE --tpu-size=v3-256 --tpu-only --noconf

TASK=byt5_xnli_zeroshot
PRETRAINED_DIR=gs://t5-data/pretrained_models/byt5/large
PRETRAINED_STEPS=1000000
FINETUNE_STEPS=262144
MODEL_DIR="${BUCKET}${TASK}"

# Run fine-tuning
python -m t5.models.mesh_transformer_main \
  --tpu="${TPU}" \
  --gcp_project="${PROJECT}" \
  --tpu_zone="${ZONE}" \
  --model_dir="${MODEL_DIR}" \
  --gin_file="${PRETRAINED_DIR}/operative_config.gin" \
  --gin_param="utils.tpu_mesh_shape.tpu_topology = 'v3-256'" \
  --gin_param="MIXTURE_NAME = '${TASK}'" \
  --gin_param="utils.run.train_steps=$((PRETRAINED_STEPS+FINETUNE_STEPS))" \
  --gin_param="utils.run.init_checkpoint='${PRETRAINED_DIR}/model.ckpt-${PRETRAINED_STEPS}'" \
  --t5_tfds_data_dir="${BUCKET}/t5-tfds" \
  --module_import="byt5.tasks"
  --gin_param="utils.run.batch_size = ('tokens_per_batch', 1048576)" \
  --gin_param="utils.run.sequence_length = {'inputs': 2048, 'targets': 56}"
  --eval_gin_param="Bitransformer.decode.max_decode_length = 56" \

The remaining experiments are shown in the tasks.py file.

Released Model Checkpoints

We have released the following checkpoints for pre-trained models described in our paper:

How to Cite

If you extend or use this work, please cite the paper where it was introduced:

@misc{xue2021byt5,
    title={ByT5: Towards a token-free future with pre-trained byte-to-byte models},
    author={Linting Xue and Aditya Barua and Noah Constant and Rami Al-Rfou and Sharan Narang and Mihir Kale and Adam Roberts and Colin Raffel},
    year={2021},
    eprint={2105.13626},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}

This is not an officially supported Google product.

Owner
Google Research
Google Research
A simple Speech Emotion Recognition (SER) API created using Flask and running in a Docker container.

keyword_searching Steps to use this Python scripts: (1)Paste this script into the file folder containing the PDF files you need to search from; (2)Thi

2 Nov 11, 2022
Switch spaces for knowledge graph embeddings

SwisE Switch spaces for knowledge graph embeddings. Requirements: python3 pytorch numpy tqdm Reproduce the results To reproduce the reported results,

Shuai Zhang 4 Dec 01, 2021
A Python script that compares files in directories

compare-files A Python script that compares files in different directories, this is similar to the command filecmp.cmp(f1, f2). I made this script in

Colvin 1 Oct 15, 2021
This repository structures data in title, summary, tags, sentiment given a fragment of a conversation

Understand-conversation-AI This repository structures data in title, summary, tags, sentiment given a fragment of a conversation How to install: pip i

Juan Camilo López Montes 1 Jan 11, 2022
I label phrases on a scale of five values: negative, somewhat negative, neutral, somewhat positive, positive

I label phrases on a scale of five values: negative, somewhat negative, neutral, somewhat positive, positive. Obstacles like sentence negation, sarcasm, terseness, language ambiguity, and many others

1 Jan 13, 2022
Malware-Related Sentence Classification

Malware-Related Sentence Classification This repo contains the code for the ICTAI 2021 paper "Enrichment of Features for Malware-Related Sentence Clas

Chau Nguyen 1 Mar 26, 2022
Fine-tuning scripts for evaluating transformer-based models on KLEJ benchmark.

The KLEJ Benchmark Baselines The KLEJ benchmark (Kompleksowa Lista Ewaluacji Językowych) is a set of nine evaluation tasks for the Polish language und

Allegro Tech 17 Oct 18, 2022
Pytorch implementation of winner from VQA Chllange Workshop in CVPR'17

2017 VQA Challenge Winner (CVPR'17 Workshop) pytorch implementation of Tips and Tricks for Visual Question Answering: Learnings from the 2017 Challeng

Mark Dong 166 Dec 11, 2022
SurvTRACE: Transformers for Survival Analysis with Competing Events

⭐ SurvTRACE: Transformers for Survival Analysis with Competing Events This repo provides the implementation of SurvTRACE for survival analysis. It is

Zifeng 13 Oct 06, 2022
Indobenchmark are collections of Natural Language Understanding (IndoNLU) and Natural Language Generation (IndoNLG)

Indobenchmark Toolkit Indobenchmark are collections of Natural Language Understanding (IndoNLU) and Natural Language Generation (IndoNLG) resources fo

Samuel Cahyawijaya 11 Aug 26, 2022
pyMorfologik MorfologikpyMorfologik - Python binding for Morfologik.

Python binding for Morfologik Morfologik is Polish morphological analyzer. For more information see http://github.com/morfologik/morfologik-stemming/

Damian Mirecki 18 Dec 29, 2021
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis Jungil Kong, Jaehyeon Kim, Jaekyoung Bae In our paper, we p

Jungil Kong 1.1k Jan 02, 2023
A text augmentation tool for named entity recognition.

neraug This python library helps you with augmenting text data for named entity recognition. Augmentation Example Reference from An Analysis of Simple

Hiroki Nakayama 48 Oct 11, 2022
An official implementation for "CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval"

The implementation of paper CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval. CLIP4Clip is a video-text retrieval model based

ArrowLuo 456 Jan 06, 2023
Training and evaluation codes for the BertGen paper (ACL-IJCNLP 2021)

BERTGEN This repository is the implementation of the paper "BERTGEN: Multi-task Generation through BERT" (https://arxiv.org/abs/2106.03484). The codeb

<a href=[email protected]"> 9 Oct 26, 2022
Understanding the Difficulty of Training Transformers

Admin Understanding the Difficulty of Training Transformers Guided by our analyses, we propose Adaptive Model Initialization (Admin), which successful

Liyuan Liu 300 Dec 29, 2022
DataCLUE: 国内首个以数据为中心的AI测评(含模型分析报告)

DataCLUE 以数据为中心的AI测评(DataCLUE) DataCLUE: A Chinese Data-centric Language Evaluation Benchmark 内容导引 章节 描述 简介 介绍以数据为中心的AI测评(DataCLUE)的背景 任务描述 任务描述 实验结果

CLUE benchmark 135 Dec 22, 2022
Explore different way to mix speech model(wav2vec2, hubert) and nlp model(BART,T5,GPT) together

SpeechMix Explore different way to mix speech model(wav2vec2, hubert) and nlp model(BART,T5,GPT) together. Introduction For the same input: from datas

Eric Lam 31 Nov 07, 2022
Korean stereoypte detector with TUNiB-Electra and K-StereoSet

Korean Stereotype Detector Korean stereotype sentence classifier using K-StereoSet with TUNiB-Electra Web demo you can test this model easily in demo

Sae_Chan_Oh 11 Feb 18, 2022
Lattice methods in TensorFlow

TensorFlow Lattice TensorFlow Lattice is a library that implements constrained and interpretable lattice based models. It is an implementation of Mono

504 Dec 20, 2022