@article{greedylayerpruningdecreasinginference,
  title = {Greedy-layer Pruning: Speeding up Transformer Models for Natural Language Processing},
  author = {David Peer and Sebastian Stabinger and Stefan Engl and Antonio Rodriguez-Sanchez},
  year = {2021},
  eprint = {2105.14839},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2105.14839v2},
}