oBERT-6-downstream-pruned-block4-80-QAT-squadv1

This model is obtained with The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models.

It corresponds to the model presented in the Table 3 - 6 Layers - Sparsity 80% - 4-block + QAT.

Pruning method: oBERT downstream block-4 + QAT
Paper: https://arxiv.org/abs/2203.07259
Dataset: SQuADv1
Sparsity: 80%
Number of layers: 6

The dev-set performance of this model:

EM = 78.28
F1 = 86.10

Code: https://github.com/neuralmagic/sparseml/tree/main/research/optimal_BERT_surgeon_oBERT

If you find the model useful, please consider citing our work.

Citation info

@article{kurtic2022optimal,
  title={The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models},
  author={Kurtic, Eldar and Campos, Daniel and Nguyen, Tuan and Frantar, Elias and Kurtz, Mark and Fineran, Benjamin and Goin, Michael and Alistarh, Dan},
  journal={arXiv preprint arXiv:2203.07259},
  year={2022}
}