@article{ngptnormalizedtransformerwith,
  title = {nGPT: Normalized Transformer with Representation Learning on the Hypersphere},
  author = {Ilya Loshchilov and Cheng-Ping Hsieh and Simeng Sun and Boris Ginsburg},
  year = {2024},
  eprint = {2410.01131},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.01131v1},
}