@article{obertaimprovingsparsetransferlearningvia, title = {oBERTa: Improving Sparse Transfer Learning via improved initialization, distillation, and pruning regimes}, author = {Daniel Campos and Alexandre Marques and Mark Kurtz and ChengXiang Zhai}, year = {2023}, eprint = {2303.17612}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2303.17612v3}, }