metadata

tags:
  - bert
  - oBERT
  - sparsity
  - pruning
  - compression
language: en
datasets: squad

oBERT-12-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 - 12 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: 12

The dev-set performance of this model:

EM = 80.58
F1 = 87.89

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}
}