cff-version: 1.2.0
message: "If you use this software, please cite it as below."
title: "huggingface/datasets"
authors:
- family-names: Lhoest
  given-names: Quentin
- family-names: Villanova del Moral
  given-names: Albert
  orcid: "https://orcid.org/0000-0003-1727-1045"
- family-names: von Platen
  given-names: Patrick
- family-names: Wolf
  given-names: Thomas
- family-names: Šaško
  given-names: Mario
- family-names: Jernite
  given-names: Yacine
- family-names: Thakur
  given-names: Abhishek
- family-names: Tunstall
  given-names: Lewis
- family-names: Patil
  given-names: Suraj
- family-names: Drame
  given-names: Mariama
- family-names: Chaumond
  given-names: Julien
- family-names: Plu
  given-names: Julien
- family-names: Davison
  given-names: Joe
- family-names: Brandeis
  given-names: Simon
- family-names: Sanh
  given-names: Victor
- family-names: Le Scao
  given-names: Teven
- family-names: Canwen Xu
  given-names: Kevin
- family-names: Patry
  given-names: Nicolas
- family-names: Liu
  given-names: Steven
- family-names: McMillan-Major
  given-names: Angelina
- family-names: Schmid
  given-names: Philipp
- family-names: Gugger
  given-names: Sylvain
- family-names: Raw
  given-names: Nathan
- family-names: Lesage
  given-names: Sylvain
- family-names: Lozhkov
  given-names: Anton
- family-names: Carrigan
  given-names: Matthew
- family-names: Matussière
  given-names: Théo
- family-names: von Werra
  given-names: Leandro
- family-names: Debut
  given-names: Lysandre
- family-names: Bekman
  given-names: Stas
- family-names: Delangue
  given-names: Clément
doi: 10.5281/zenodo.4817768
repository-code: "https://github.com/huggingface/datasets"
license: Apache-2.0
preferred-citation:
  type: conference-paper
  title: "Datasets: A Community Library for Natural Language Processing"
  authors:
  - family-names: Lhoest
    given-names: Quentin
  - family-names: Villanova del Moral
    given-names: Albert
    orcid: "https://orcid.org/0000-0003-1727-1045"
  - family-names: von Platen
    given-names: Patrick
  - family-names: Wolf
    given-names: Thomas
  - family-names: Šaško
    given-names: Mario
  - family-names: Jernite
    given-names: Yacine
  - family-names: Thakur
    given-names: Abhishek
  - family-names: Tunstall
    given-names: Lewis
  - family-names: Patil
    given-names: Suraj
  - family-names: Drame
    given-names: Mariama
  - family-names: Chaumond
    given-names: Julien
  - family-names: Plu
    given-names: Julien
  - family-names: Davison
    given-names: Joe
  - family-names: Brandeis
    given-names: Simon
  - family-names: Sanh
    given-names: Victor
  - family-names: Le Scao
    given-names: Teven
  - family-names: Canwen Xu
    given-names: Kevin
  - family-names: Patry
    given-names: Nicolas
  - family-names: Liu
    given-names: Steven
  - family-names: McMillan-Major
    given-names: Angelina
  - family-names: Schmid
    given-names: Philipp
  - family-names: Gugger
    given-names: Sylvain
  - family-names: Raw
    given-names: Nathan
  - family-names: Lesage
    given-names: Sylvain
  - family-names: Lozhkov
    given-names: Anton
  - family-names: Carrigan
    given-names: Matthew
  - family-names: Matussière
    given-names: Théo
  - family-names: von Werra
    given-names: Leandro
  - family-names: Debut
    given-names: Lysandre
  - family-names: Bekman
    given-names: Stas
  - family-names: Delangue
    given-names: Clément
  collection-title: "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations"
  collection-type: proceedings
  month: 11
  year: 2021
  publisher:
    name: "Association for Computational Linguistics"
  url: "https://aclanthology.org/2021.emnlp-demo.21"
  start: 175
  end: 184
  identifiers:
    - type: other
      value: "arXiv:2109.02846"
      description: "The arXiv preprint of the paper"