@misc{ding2023longnet, title={LongNet: Scaling Transformers to 1,000,000,000 Tokens}, author={Jiayu Ding and Shuming Ma and Li Dong and Xingxing Zhang and Shaohan Huang and Wenhui Wang and Furu Wei}, year={2023}, eprint={2307.02486}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2307.02486} }