{
 "id": "BAAI/IndustryCorpus_law",
 "owner": "BAAI",
 "name": "IndustryCorpus_law",
 "downloads": 6863,
 "likes": 3,
 "last_modified": "2026-08-19T19:44:47.000Z",
 "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": "@misc{shi2024industrycorpus,\n  title     = {IndustryCorpus: Multilingual Multi-Industry Pre-Training Data},\n  author    = {Xiaofeng Shi and Lulu Zhao and Hua Zhou and Donglin Hao},\n  year      = {2024},\n  publisher = {Hugging Face},\n  url       = {https://huggingface.co/datasets/BAAI/IndustryCorpus}\n}",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive."
}