@misc{sun2023retentive, title={Retentive Network: A Successor to Transformer for Large Language Models}, author={Yutao Sun and Li Dong and Shaohan Huang and Shuming Ma and Yuqing Xia and Jilong Xue and Jianyong Wang and Furu Wei}, year={2023}, eprint={2307.08621}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2307.08621} }