@article{deepnetscalingtransformersto1000layers, title = {DeepNet: Scaling Transformers to 1,000 Layers}, author = {Hongyu Wang and Shuming Ma and Li Dong and Shaohan Huang and Dongdong Zhang and Furu Wei}, year = {2022}, eprint = {2203.00555}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2203.00555v1}, }