🌟 New model addition: FNet

# 🌟 New model addition: FNet

FNet is a highly efficient Transformer-like encoder architecture, wherein the self-attention sublayers have been wholly replaced by standard, unparameterized Fourier Transforms.

I would like to help adding this!

## Open source status

* [x] the model implementation is available: https://github.com/google-research/google-research/tree/master/f_net
* [x] the model weights are available: https://github.com/google-research/google-research/tree/master/f_net
* [x] who are the authors: (@ilyaeck @santiontanon) (Not sure, googled the authors' name + github, sorry if it's incorrect)