{
 "id": "OptimalScale/ClimbLab",
 "owner": "OptimalScale",
 "name": "ClimbLab",
 "downloads": 9911,
 "likes": 17,
 "last_modified": "2025-05-04T03:48:49.000Z",
 "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": "@article{diao2025climb,\n  author    = {Shizhe Diao and Yu Yang and Yonggan Fu and Xin Dong and Dan Su and Markus Kliegl and Zijia Chen and Peter Belcak and Yoshi Suhara and Hongxu Yin and Mostofa Patwary and Celine Lin and Jan Kautz and Pavlo Molchanov},\n  title={CLIMB: CLustering-based Iterative Data Mixture Bootstrapping for Language Model Pre-training}, \n  journal   = {arXiv preprint},\n  year      = {2025},\n  archivePrefix = {arXiv},\n  primaryClass = {cs.CL},\n  url={https://arxiv.org/abs/2504.13161}, \n}",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive."
}