---
tags:
- bert
- oBERT
- sparsity
- pruning
- compression
language: en
datasets:
- bookcorpus
- wikipedia
---
# oBERT-12-upstream-pruned-unstructured-97-v2

This model is obtained with [The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models](https://arxiv.org/abs/2203.07259).


It corresponds to the upstream pruned model used as a starting point for sparse-transfer learning to downstream tasks presented in the `Table 2 - oBERT - {SQuADv1, MNLI, QQP} - 97%` (in the upcoming updated version of the paper).

Finetuned versions of this model for each downstream task are:

- SQuADv1: `neuralmagic/oBERT-12-upstream-pruned-unstructured-97-finetuned-squadv1-v2`
- MNLI: `neuralmagic/oBERT-12-upstream-pruned-unstructured-97-finetuned-mnli-v2`
- QQP: `neuralmagic/oBERT-12-upstream-pruned-unstructured-97-finetuned-qqp-v2`

```
Pruning method: oBERT upstream unstructured
Paper: https://arxiv.org/abs/2203.07259
Dataset: BookCorpus and English Wikipedia
Sparsity: 97%
Number of layers: 12
```

Code: [https://github.com/neuralmagic/sparseml/tree/main/research/optimal_BERT_surgeon_oBERT](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
```bibtex
@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}
}
```