{
 "id": "MichaelR207/high-quality-cc-21b",
 "owner": "MichaelR207",
 "name": "high-quality-cc-21b",
 "downloads": 1132,
 "likes": 0,
 "last_modified": "2026-06-24T23:26:34.000Z",
 "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": "@misc{high_quality_cc_21b,\n  title  = {high_quality: An LLM-extracted high-quality web text corpus from Common Crawl},\n  author = {MichaelR207},\n  year   = {2026},\n  note   = {Derived from Common Crawl.}\n}",
 "signal": "permissive",
 "reason": "The declared licence (odc-by) is classified as permissive.",
 "revision": "537b2a8891038077ffa2ca485fbd0dc891971256",
 "stated_evidence": "https://huggingface.co/datasets/MichaelR207/high-quality-cc-21b/blob/537b2a8891038077ffa2ca485fbd0dc891971256/README.md",
 "file_evidence": "https://huggingface.co/datasets/MichaelR207/high-quality-cc-21b/tree/537b2a8891038077ffa2ca485fbd0dc891971256",
 "card_nc": false
}