ekurtic's picture
Add link to code
24d8c1b
---
tags:
- bert
- oBERT
- sparsity
- pruning
- compression
language: en
datasets: squad
---
# oBERT-12-downstream-pruned-unstructured-90-squadv1
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 model presented in the `Table 1 - 30 Epochs - oBERT - SQuADv1 90%`.
```
Pruning method: oBERT downstream unstructured
Paper: https://arxiv.org/abs/2203.07259
Dataset: SQuADv1
Sparsity: 90%
Number of layers: 12
```
The dev-set performance reported in the paper is averaged over three seeds, and we release the best model (marked with `(*)`):
```
| oBERT 90% | F1 | EM |
| ------------ | ----- | ----- |
| seed=42 | 88.22 | 81.10 |
| seed=3407 (*)| 88.46 | 81.26 |
| seed=54321 | 88.26 | 81.00 |
| ------------ | ----- | ----- |
| mean | 88.31 | 81.12 |
| stdev | 0.128 | 0.131 |
```
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}
}
```