{
 "id": "coral-nlp/german-commons",
 "owner": "coral-nlp",
 "name": "german-commons",
 "downloads": 4534,
 "likes": 41,
 "last_modified": "2026-01-22T10:35:42.000Z",
 "stated_licence": "odc-by",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "@article{gienapp:2025d,\n\ttitle        = {{The German Commons -- 154 Billion Tokens of Openly Licensed Text for German Language Models}},\n\tauthor       = {Lukas Gienapp and\n                    Christopher Schr\\\"oder and\n                    Stefan Schweter and\n                    Christopher Akiki and\n                    Ferdinand Schlatt and\n                    Arden Zimmermann and\n                    Phillipe Gen\\^et and\n                    Martin Potthast},\n\tyear         = 2025,\n\tmonth        = oct,\n\tjournal      = {CoRR},\n\tvolume       = {abs/2510.13996},\n\turl          = {https://arxiv.org/abs/2510.13996}\n}",
 "signal": "permissive",
 "reason": "The declared licence (odc-by) is classified as permissive.",
 "revision": "d12379bba6ecdc525958ebe6e182f9cb905a06e2",
 "stated_evidence": "https://huggingface.co/datasets/coral-nlp/german-commons/blob/d12379bba6ecdc525958ebe6e182f9cb905a06e2/README.md",
 "file_evidence": "https://huggingface.co/datasets/coral-nlp/german-commons/tree/d12379bba6ecdc525958ebe6e182f9cb905a06e2",
 "card_nc": false
}