@article{modulartransformerscompressingtransforme, title = {Modular Transformers: Compressing Transformers into Modularized Layers for Flexible Efficient Inference}, author = {Wangchunshu Zhou and Ronan Le Bras and Yejin Choi}, year = {2023}, eprint = {2306.02379}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2306.02379v1}, }