{
 "id": "JeanKaddour/minipile",
 "owner": "JeanKaddour",
 "name": "minipile",
 "downloads": 2531,
 "likes": 155,
 "last_modified": "2023-06-20T10:08:26.000Z",
 "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{kaddour2023minipile,\n  title={The MiniPile Challenge for Data-Efficient Language Models},\n  author={Kaddour, Jean},\n  journal={arXiv preprint arXiv:2304.08442},\n  year={2023}\n}\n\n@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}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "18ad1b0c701eaa0de03d3cecfdd769cbc70ffbd0",
 "stated_evidence": "https://huggingface.co/datasets/JeanKaddour/minipile/blob/18ad1b0c701eaa0de03d3cecfdd769cbc70ffbd0/README.md",
 "file_evidence": "https://huggingface.co/datasets/JeanKaddour/minipile/tree/18ad1b0c701eaa0de03d3cecfdd769cbc70ffbd0",
 "card_nc": false
}