Introduction

Fairseq(-py) is a sequence modeling toolkit that allows researchers and developers to train custom models for translation, summarization, language modeling and other text generation tasks. It provides reference implementations of various sequence-to-sequence models, including:

• Convolutional Neural Networks (CNN)
  • Dauphin et al. (2017): Language Modeling with Gated Convolutional Networks
  • Gehring et al. (2017): Convolutional Sequence to Sequence Learning
  • Edunov et al. (2018): Classical Structured Prediction Losses for Sequence to Sequence Learning
  • New Fan et al. (2018): Hierarchical Neural Story Generation
• Long Short-Term Memory (LSTM) networks
  • Luong et al. (2015): Effective Approaches to Attention-based Neural Machine Translation
  • Wiseman and Rush (2016): Sequence-to-Sequence Learning as Beam-Search Optimization
• Transformer (self-attention) networks
  • Vaswani et al. (2017): Attention Is All You Need
  • New Ott et al. (2018): Scaling Neural Machine Translation
  • New Edunov et al. (2018): Understanding Back-Translation at Scale

Fairseq features:

• multi-GPU (distributed) training on one machine or across multiple machines
• fast beam search generation on both CPU and GPU
• large mini-batch training even on a single GPU via delayed updates
• fast half-precision floating point (FP16) training
• extensible: easily register new models, criterions, and tasks

We also provide pre-trained models for several benchmark translation and language modeling datasets.

Requirements and Installation

• A PyTorch installation
• For training new models, you'll also need an NVIDIA GPU and NCCL
• Python version 3.6

Currently fairseq requires PyTorch version >= 0.4.0. Please follow the instructions here: https://github.com/pytorch/pytorch#installation.

If you use Docker make sure to increase the shared memory size either with --ipc=host or --shm-size as command line options to nvidia-docker run.

After PyTorch is installed, you can install fairseq with:

pip install -r requirements.txt
python setup.py build develop

Getting Started

The full documentation contains instructions for getting started, training new models and extending fairseq with new model types and tasks.

Pre-trained Models

We provide the following pre-trained models and pre-processed, binarized test sets:

Translation

Description	Dataset	Model	Test set(s)
Convolutional (Gehring et al., 2017)	WMT14 English-French	download (.tar.bz2)	newstest2014: download (.tar.bz2) newstest2012/2013: download (.tar.bz2)
Convolutional (Gehring et al., 2017)	WMT14 English-German	download (.tar.bz2)	newstest2014: download (.tar.bz2)
Convolutional (Gehring et al., 2017)	WMT17 English-German	download (.tar.bz2)	newstest2014: download (.tar.bz2)
Transformer (Ott et al., 2018)	WMT14 English-French	download (.tar.bz2)	newstest2014 (shared vocab): download (.tar.bz2)
Transformer (Ott et al., 2018)	WMT16 English-German	download (.tar.bz2)	newstest2014 (shared vocab): download (.tar.bz2)
Transformer (Edunov et al., 2018; WMT'18 winner)	WMT'18 English-German	download (.tar.bz2)	See NOTE in the archive

Language models

Description	Dataset	Model	Test set(s)
Convolutional (Dauphin et al., 2017)	Google Billion Words	download (.tar.bz2)	download (.tar.bz2)
Convolutional (Dauphin et al., 2017)	WikiText-103	download (.tar.bz2)	download (.tar.bz2)

Stories

Description	Dataset	Model	Test set(s)
Stories with Convolutional Model (Fan et al., 2018)	WritingPrompts	download (.tar.bz2)	download (.tar.bz2)

Usage

Generation with the binarized test sets can be run in batch mode as follows, e.g. for WMT 2014 English-French on a GTX-1080ti:

$ curl https://s3.amazonaws.com/fairseq-py/models/wmt14.v2.en-fr.fconv-py.tar.bz2 | tar xvjf - -C data-bin
$ curl https://s3.amazonaws.com/fairseq-py/data/wmt14.v2.en-fr.newstest2014.tar.bz2 | tar xvjf - -C data-bin
$ python generate.py data-bin/wmt14.en-fr.newstest2014  \
  --path data-bin/wmt14.en-fr.fconv-py/model.pt \
  --beam 5 --batch-size 128 --remove-bpe | tee /tmp/gen.out
...
| Translated 3003 sentences (96311 tokens) in 166.0s (580.04 tokens/s)
| Generate test with beam=5: BLEU4 = 40.83, 67.5/46.9/34.4/25.5 (BP=1.000, ratio=1.006, syslen=83262, reflen=82787)

# Scoring with score.py:
$ grep ^H /tmp/gen.out | cut -f3- > /tmp/gen.out.sys
$ grep ^T /tmp/gen.out | cut -f2- > /tmp/gen.out.ref
$ python score.py --sys /tmp/gen.out.sys --ref /tmp/gen.out.ref
BLEU4 = 40.83, 67.5/46.9/34.4/25.5 (BP=1.000, ratio=1.006, syslen=83262, reflen=82787)

Join the fairseq community

• Facebook page: https://www.facebook.com/groups/fairseq.users
• Google group: https://groups.google.com/forum/#!forum/fairseq-users

Citation

If you use the code in your paper, then please cite it as:

@inproceedings{gehring2017convs2s,
  author    = {Gehring, Jonas, and Auli, Michael and Grangier, David and Yarats, Denis and Dauphin, Yann N},
  title     = "{Convolutional Sequence to Sequence Learning}",
  booktitle = {Proc. of ICML},
  year      = 2017,
}

License

fairseq(-py) is BSD-licensed. The license applies to the pre-trained models as well. We also provide an additional patent grant.

Credits

This is a PyTorch version of fairseq, a sequence-to-sequence learning toolkit from Facebook AI Research. The original authors of this reimplementation are (in no particular order) Sergey Edunov, Myle Ott, and Sam Gross.