Views
No views yet
Table 3 - 12 Layers - Sparsity 90% - 4-block.Pruning method: oBERT downstream block-4
Paper: https://arxiv.org/abs/2203.07259
Dataset: SQuADv1
Sparsity: 90%
Number of layers: 12EM = 80.14
F1 = 87.571@article{kurtic2022optimal,
2 title={The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models},
3 author={Kurtic, Eldar and Campos, Daniel and Nguyen, Tuan and Frantar, Elias and Kurtz, Mark and Fineran, Benjamin and Goin, Michael and Alistarh, Dan},
4 journal={arXiv preprint arXiv:2203.07259},
5 year={2022}
6}