H-D-T/Buzz-V1.2

Citation text from the card

@misc{ibrahim2024simple,
      title={Simple and Scalable Strategies to Continually Pre-train Large Language Models}, 
      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},
      year={2024},
      eprint={2403.08763},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}

@misc{jain2023neftune,
      title={NEFTune: Noisy Embeddings Improve Instruction Finetuning}, 
      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},
      year={2023},
      eprint={2310.05914},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

@misc{wang2020optimistic,
      title={An Optimistic Acceleration of AMSGrad for Nonconvex Optimization}, 
      author={Jun-Kun Wang and Xiaoyun Li and Belhal Karimi and Ping Li},
      year={2020},
      eprint={1903.01435},
      archivePrefix={arXiv},
      primaryClass={stat.ML}
}

@misc{keskar2017improving,
      title={Improving Generalization Performance by Switching from Adam to SGD}, 
      author={Nitish Shirish Keskar and Richard Socher},
      year={2017},
      eprint={1712.07628},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}

@misc{mukherjee2023orca,
      title={Orca: Progressive Learning from Complex Explanati

All datasets marked Permissive or share-alike | JSON