{
 "id": "ZhuofengLi/fineweb-edu-pretokenized-llama3-100b",
 "owner": "ZhuofengLi",
 "name": "fineweb-edu-pretokenized-llama3-100b",
 "downloads": 862,
 "likes": 0,
 "last_modified": "2026-07-21T20:10:25.000Z",
 "stated_licence": "odc-by",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "The upstream [FineWeb-Edu dataset](https://huggingface.co/datasets/HuggingFaceFW/fineweb-edu) is released under [ODC-BY](https://opendatacommons.org/licenses/by/). This derivative retains that license and should be attributed to FineWeb-Edu / Hugging Face as well as this preprocessing repository. Please consult the upstream dataset card for its documentation, provenance, and usage considerations.",
 "signal": "permissive",
 "reason": "The declared licence (odc-by) is classified as permissive.",
 "revision": "d4914cb8fdbdc80bdc1e965d8c689bd9a445315a",
 "stated_evidence": "https://huggingface.co/datasets/ZhuofengLi/fineweb-edu-pretokenized-llama3-100b/blob/d4914cb8fdbdc80bdc1e965d8c689bd9a445315a/README.md",
 "file_evidence": "https://huggingface.co/datasets/ZhuofengLi/fineweb-edu-pretokenized-llama3-100b/tree/d4914cb8fdbdc80bdc1e965d8c689bd9a445315a",
 "card_nc": false
}