The PyTorch implementation of FNet from the paper FNet: Mixing Tokens with Fourier Transforms.
@inproceedings{lee-thorp-etal-2022-fnet,
title = {FNet: Mixing Tokens with Fourier Transforms},
author = {Lee-Thorp, James and Ainslie, Joshua and Eckstein, Ilya and Ontanon, Santiago},
booktitle = {Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
month = {07},
year = {2022},
publisher = {Association for Computational Linguistics},
pages = {4296--4313}
}
- Create a data folder:
mkdir data
- Download the dataset compressed archive
wget $URL
- Decompress the dataset compressed archive and put the contents into the data folder
unzip $dataset.zip
mv $datast ./data/$datast
- Run the main file
python $dataset_main.py --task="$task"
To install requirements:
pip3 install -r requirements.txt