{
 "id": "GenerTeam/pretrain_data_eukaryote",
 "owner": "GenerTeam",
 "name": "pretrain_data_eukaryote",
 "downloads": 2846,
 "likes": 5,
 "last_modified": "2026-05-11T14:11:42.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "@article {li2026generator2,\n\tauthor = {Li, Qiuyi and Zhan, Zhihao and Feng, Shikun and Zhu, Yiheng and He, Yuan and Wu, Wei and Shi, Zhenghang and Wang, Shengjie and Hu, Zongyong and Yang, Zhao and Li, Jiaoyang and Tang, Jian and Liu, Haiguang and Qin, Tao},\n\ttitle = {GENERator-v2: Reconciling Coarse Tokenization with Single-Nucleotide Resolution in Genomic Language Modeling},\n\telocation-id = {2026.01.27.702015},\n\tyear = {2026},\n\tdoi = {10.64898/2026.01.27.702015},\n\tpublisher = {Cold Spring Harbor Laboratory},\n\tURL = {https://www.biorxiv.org/content/early/2026/05/04/2026.01.27.702015},\n\tjournal = {bioRxiv}\n}\n\n@article{wu2025generator,\n  title={GENERator: a long-context generative genomic foundation model},\n  author={Wu, Wei and Li, Qiuyi and Li, Mingyang and Fu, Kun and Feng, Fuli and Ye, Jieping and Xiong, Hui and Wang, Zheng},\n  journal={arXiv preprint arXiv:2502.07272},\n  year={2025}\n}",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "76cf529c4898ed6c1aaed97bff912a45837d1794",
 "stated_evidence": "https://huggingface.co/datasets/GenerTeam/pretrain_data_eukaryote/blob/76cf529c4898ed6c1aaed97bff912a45837d1794/README.md",
 "file_evidence": "https://huggingface.co/datasets/GenerTeam/pretrain_data_eukaryote/tree/76cf529c4898ed6c1aaed97bff912a45837d1794",
 "card_nc": false
}