@article{zydaa13tdatasetforopenlanguage,
  title = {Zyda: A 1.3T Dataset for Open Language Modeling},
  author = {Yury Tokpanov and Beren Millidge and Paolo Glorioso and Jonathan Pilault and Adam Ibrahim and James Whittington and Quentin Anthony},
  year = {2024},
  eprint = {2406.01981},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.01981v2},
}