{
 "id": "EleutherAI/pile",
 "owner": "EleutherAI",
 "name": "pile",
 "downloads": 6761,
 "likes": 517,
 "last_modified": "2023-05-03T15:58:14.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation",
  "fill-mask"
 ],
 "citation": "@article{gao2020pile,\n  title={The {P}ile: An 800{GB} dataset of diverse text for language modeling},\n  author={Gao, Leo and Biderman, Stella and Black, Sid and Golding, Laurence and Hoppe, Travis and Foster, Charles and Phang, Jason and He, Horace and Thite, Anish and Nabeshima, Noa and others},\n  journal={arXiv preprint arXiv:2101.00027},\n  year={2020}\n}\n\n\n@article{biderman2022datasheet,\n  title={Datasheet for the pile},\n  author={Biderman, Stella and Bicheno, Kieran and Gao, Leo},\n  journal={arXiv preprint arXiv:2201.07311},\n  year={2022}\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata."
}