{
 "id": "Hugodonotexit/dolma-en",
 "owner": "Hugodonotexit",
 "name": "dolma-en",
 "downloads": 107,
 "likes": 1,
 "last_modified": "2026-02-15T19:25:24.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "@article{dolma2023,\n  title   = {Dolma: An Open Corpus of Three Trillion Tokens for Language Model Pretraining},\n  author  = {Soldaini, Luca and others},\n  journal = {arXiv preprint arXiv:2305.16938},\n  year    = {2023}\n}",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "711a5584d9498cd7d1c1191cb347035172728b89",
 "stated_evidence": "https://huggingface.co/datasets/Hugodonotexit/dolma-en/blob/711a5584d9498cd7d1c1191cb347035172728b89/README.md",
 "file_evidence": "https://huggingface.co/datasets/Hugodonotexit/dolma-en/tree/711a5584d9498cd7d1c1191cb347035172728b89",
 "card_nc": false
}