{
 "id": "RWKV/EagleX-WorldContinued",
 "owner": "RWKV",
 "name": "EagleX-WorldContinued",
 "downloads": 431,
 "likes": 1,
 "last_modified": "2024-06-22T00:56:35.000Z",
 "stated_licence": "cc-by-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation",
  "fill-mask"
 ],
 "citation": "```latex\n@software{penedo2024fineweb,\n  author = {Penedo, Guilherme and Kydlíček, Hynek and von Werra, Leandro and Wolf, Thomas},\n  title = {FineWeb},\n  month = April,\n  year = 2024,\n  doi = { 10.57967/hf/2092 },\n  url = {https://huggingface.co/datasets/HuggingFaceFW/fineweb}\n}\n\n@article{gao2020pile,\n  title={The {P}ile: An 800{GB} dataset of diverse text for language modeling},\n  author={Gao, Leo and Biderman, Stella and Black, Sid and Golding, Laurence and Hoppe, Travis and Foster, Charles and Phang, Jason and He, Horace and Thite, Anish and Nabeshima, Noa and others},\n  journal={arXiv preprint arXiv:2101.00027},\n  year={2020}\n}\n\n@misc{cerebras2023slimpajama,\n  author = {Soboleva, Daria and Al-Khateeb, Faisal and Myers, Robert and Steeves, Jacob R and Hestness, Joel and Dey, Nolan},\n  title = {{SlimPajama: A 627B token cleaned and deduplicated version of RedPajama}},\n  month = June,\n  year = 2023,\n  howpublished = {\\url{https://www.cerebras.net/blog/slimpajama-a-627b-token-cleaned-and-deduplicated-version-of-redpajama}},\n  url = {https://huggingface.co/datasets/cerebras/SlimPajama-627B},\n}\n\n@misc{kudugunta2023madlad400,\n      title={MADLAD-400: A Multilingual And Document-Level Large Audited Dataset}, \n      author={Sneha Kudugunta and Isaac Caswell and Biao Zhang and Xavier Garcia and Christopher A. Choquette-Choo and Katherine Lee and Derrick Xin and Aditya Kusupati and Romi Stella and Ankur Bapna and Orhan Firat},\n      year={2023},\n      eprint={2309.04662},\n      archi",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-sa-4.0) is classified as share-alike.",
 "revision": "b3c23a3c57f5902c0abb65470a34d68820e45416",
 "stated_evidence": "https://huggingface.co/datasets/RWKV/EagleX-WorldContinued/blob/b3c23a3c57f5902c0abb65470a34d68820e45416/README.md",
 "file_evidence": "https://huggingface.co/datasets/RWKV/EagleX-WorldContinued/tree/b3c23a3c57f5902c0abb65470a34d68820e45416",
 "card_nc": false
}