All Projects → pytorch → Fairseq

pytorch / Fairseq

Licence: mit
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Programming Languages

python
139335 projects - #7 most used programming language
Cuda
1817 projects

Projects that are alternatives of or similar to Fairseq

Gretel Synthetics
Differentially private learning to create fake, synthetic datasets with enhanced privacy guarantees
Stars: ✭ 147 (-99.01%)
Mutual labels:  artificial-intelligence
Artificial Intelligence Projects
Collection of Artificial Intelligence projects.
Stars: ✭ 152 (-98.98%)
Mutual labels:  artificial-intelligence
Covergenerator Ue4
A dynamic cover point generator plugin for Unreal Engine 4.
Stars: ✭ 156 (-98.95%)
Mutual labels:  artificial-intelligence
Routing Transformer
Fully featured implementation of Routing Transformer
Stars: ✭ 149 (-99%)
Mutual labels:  artificial-intelligence
Machine Learning With Python
Practice and tutorial-style notebooks covering wide variety of machine learning techniques
Stars: ✭ 2,197 (-85.22%)
Mutual labels:  artificial-intelligence
Qb
QANTA Quiz Bowl AI
Stars: ✭ 153 (-98.97%)
Mutual labels:  artificial-intelligence
Self Driving Golf Cart
Be Driven 🚘
Stars: ✭ 147 (-99.01%)
Mutual labels:  artificial-intelligence
Stylegan2 Pytorch
Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement
Stars: ✭ 2,656 (-82.13%)
Mutual labels:  artificial-intelligence
Mariana
The Cutest Deep Learning Framework which is also a wonderful Declarative Language
Stars: ✭ 151 (-98.98%)
Mutual labels:  artificial-intelligence
Sinkhorn Transformer
Sinkhorn Transformer - Practical implementation of Sparse Sinkhorn Attention
Stars: ✭ 156 (-98.95%)
Mutual labels:  artificial-intelligence
Forecasting
Time Series Forecasting Best Practices & Examples
Stars: ✭ 2,123 (-85.71%)
Mutual labels:  artificial-intelligence
Hands On Machine Learning With Scikit Learn Keras And Tensorflow
Notes & exercise solutions of Part I from the book: "Hands-On ML with Scikit-Learn, Keras & TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems" by Aurelien Geron
Stars: ✭ 151 (-98.98%)
Mutual labels:  artificial-intelligence
Computer Vision Video Lectures
A curated list of free, high-quality, university-level courses with video lectures related to the field of Computer Vision.
Stars: ✭ 154 (-98.96%)
Mutual labels:  artificial-intelligence
Stanford Cs 221 Artificial Intelligence
VIP cheatsheets for Stanford's CS 221 Artificial Intelligence
Stars: ✭ 1,923 (-87.06%)
Mutual labels:  artificial-intelligence
Java Deep Learning Cookbook
Code for Java Deep Learning Cookbook
Stars: ✭ 156 (-98.95%)
Mutual labels:  artificial-intelligence
Floyd Cli
Command line tool for FloydHub - the fastest way to build, train, and deploy deep learning models
Stars: ✭ 147 (-99.01%)
Mutual labels:  artificial-intelligence
Df Ai
Dwarf Fortress + Artificial Intelligence
Stars: ✭ 151 (-98.98%)
Mutual labels:  artificial-intelligence
Airsim
Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research
Stars: ✭ 12,528 (-15.7%)
Mutual labels:  artificial-intelligence
Best ai paper 2020
A curated list of the latest breakthroughs in AI by release date with a clear video explanation, link to a more in-depth article, and code
Stars: ✭ 2,140 (-85.6%)
Mutual labels:  artificial-intelligence
Awesome Machine Learning Startups Berlin
🤖 A curated list of machine learning & artificial intelligence startups in Berlin (Germany)
Stars: ✭ 154 (-98.96%)
Mutual labels:  artificial-intelligence



MIT License Latest Release Build Status Documentation Status


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.

We provide reference implementations of various sequence modeling papers:

List of implemented papers

What's New:

Previous updates

Features:

We also provide pre-trained models for translation and language modeling with a convenient torch.hub interface:

en2de = torch.hub.load('pytorch/fairseq', 'transformer.wmt19.en-de.single_model')
en2de.translate('Hello world', beam=5)
# 'Hallo Welt'

See the PyTorch Hub tutorials for translation and RoBERTa for more examples.

Requirements and Installation

  • PyTorch version >= 1.5.0
  • Python version >= 3.6
  • For training new models, you'll also need an NVIDIA GPU and NCCL
  • To install fairseq and develop locally:
git clone https://github.com/pytorch/fairseq
cd fairseq
pip install --editable ./

# on MacOS:
# CFLAGS="-stdlib=libc++" pip install --editable ./

# to install the latest stable release (0.10.x)
# pip install fairseq
  • For faster training install NVIDIA's apex library:
git clone https://github.com/NVIDIA/apex
cd apex
pip install -v --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" \
  --global-option="--deprecated_fused_adam" --global-option="--xentropy" \
  --global-option="--fast_multihead_attn" ./
  • For large datasets install PyArrow: pip install pyarrow
  • 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 .

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 and examples

We provide pre-trained models and pre-processed, binarized test sets for several tasks listed below, as well as example training and evaluation commands.

We also have more detailed READMEs to reproduce results from specific papers:

Join the fairseq community

License

fairseq(-py) is MIT-licensed. The license applies to the pre-trained models as well.

Citation

Please cite as:

@inproceedings{ott2019fairseq,
  title = {fairseq: A Fast, Extensible Toolkit for Sequence Modeling},
  author = {Myle Ott and Sergey Edunov and Alexei Baevski and Angela Fan and Sam Gross and Nathan Ng and David Grangier and Michael Auli},
  booktitle = {Proceedings of NAACL-HLT 2019: Demonstrations},
  year = {2019},
}
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].