@article{branchnormrobustlyscalingextremelydeep, title = {BranchNorm: Robustly Scaling Extremely Deep Transformers}, author = {Yijin Liu and Xianfeng Zeng and Fandong Meng and Jie zhou}, year = {2023}, eprint = {2305.02790}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2305.02790v1}, }