Implementation of Hourglass Transformer, in Pytorch, from Google and OpenAI

@misc{nawrot2021hierarchical,
    title   = {Hierarchical Transformers Are More Efficient Language Models}, 
    author  = {Piotr Nawrot and Szymon Tworkowski and Michał Tyrolski and Łukasz Kaiser and Yuhuai Wu and Christian Szegedy and Henryk Michalewski},
    year    = {2021},
    eprint  = {2110.13711},
    archivePrefix = {arXiv},
    primaryClass = {cs.LG}
}