{
 "id": "H-D-T/Buzz-V1.2",
 "owner": "H-D-T",
 "name": "Buzz-V1.2",
 "downloads": 658,
 "likes": 12,
 "last_modified": "2024-10-30T03:03:07.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@misc{ibrahim2024simple,\n      title={Simple and Scalable Strategies to Continually Pre-train Large Language Models}, \n      author={Adam Ibrahim and Benjamin Thérien and Kshitij Gupta and Mats L. Richter and Quentin Anthony and Timothée Lesort and Eugene Belilovsky and Irina Rish},\n      year={2024},\n      eprint={2403.08763},\n      archivePrefix={arXiv},\n      primaryClass={cs.LG}\n}\n\n@misc{jain2023neftune,\n      title={NEFTune: Noisy Embeddings Improve Instruction Finetuning}, \n      author={Neel Jain and Ping-yeh Chiang and Yuxin Wen and John Kirchenbauer and Hong-Min Chu and Gowthami Somepalli and Brian R. Bartoldson and Bhavya Kailkhura and Avi Schwarzschild and Aniruddha Saha and Micah Goldblum and Jonas Geiping and Tom Goldstein},\n      year={2023},\n      eprint={2310.05914},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL}\n}\n\n@misc{wang2020optimistic,\n      title={An Optimistic Acceleration of AMSGrad for Nonconvex Optimization}, \n      author={Jun-Kun Wang and Xiaoyun Li and Belhal Karimi and Ping Li},\n      year={2020},\n      eprint={1903.01435},\n      archivePrefix={arXiv},\n      primaryClass={stat.ML}\n}\n\n@misc{keskar2017improving,\n      title={Improving Generalization Performance by Switching from Adam to SGD}, \n      author={Nitish Shirish Keskar and Richard Socher},\n      year={2017},\n      eprint={1712.07628},\n      archivePrefix={arXiv},\n      primaryClass={cs.LG}\n}\n\n@misc{mukherjee2023orca,\n      title={Orca: Progressive Learning from Complex Explanati",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "7966258a061f1cb9d6c753f06311157c65467912",
 "stated_evidence": "https://huggingface.co/datasets/H-D-T/Buzz-V1.2/blob/7966258a061f1cb9d6c753f06311157c65467912/README.md",
 "file_evidence": "https://huggingface.co/datasets/H-D-T/Buzz-V1.2/tree/7966258a061f1cb9d6c753f06311157c65467912",
 "card_nc": false
}