A fork for fairseq, migrated to DVC and used for NLP research.
|
1 year ago | |
---|---|---|
.dvc | 2 years ago | |
docs | 2 years ago | |
dvc-example | 1 year ago | |
examples | 2 years ago | |
fairseq | 1 year ago | |
scripts | 2 years ago | |
tests | 2 years ago | |
.gitignore | 2 years ago | |
CONTRIBUTING.md | 3 years ago | |
LICENSE | 3 years ago | |
PATENTS | 3 years ago | |
README.md | 2 years ago | |
eval_lm.py | 2 years ago | |
fairseq.gif | 3 years ago | |
fairseq_logo.png | 2 years ago | |
generate.py | 1 year ago | |
interactive.py | 2 years ago | |
preprocess.py | 2 years ago | |
requirements.txt | 2 years ago | |
score.py | 2 years ago | |
setup.py | 2 years ago | |
train.py | 1 year ago |
Legend |
---|
DVC Managed File |
Git Managed File |
Metric |
Stage File |
External File |
Legend |
---|
DVC Managed File |
Git Managed File |
Metric |
Stage File |
External File |
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:
Fairseq features:
We also provide pre-trained models for several benchmark translation and language modeling datasets.
Currently fairseq requires PyTorch version >= 1.0.0. 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
The full documentation contains instructions for getting started, training new models and extending fairseq with new model types and tasks.
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:
fairseq(-py) is BSD-licensed. The license applies to the pre-trained models as well. We also provide an additional patent grant.
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.