|
--- |
|
tags: |
|
- bert |
|
- oBERT |
|
- sparsity |
|
- pruning |
|
- compression |
|
language: en |
|
datasets: mnli |
|
--- |
|
# oBERT-12-downstream-pruned-unstructured-80-mnli |
|
|
|
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 - MNLI 80%`. |
|
|
|
``` |
|
Pruning method: oBERT downstream unstructured |
|
Paper: https://arxiv.org/abs/2203.07259 |
|
Dataset: MNLI |
|
Sparsity: 80% |
|
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 80% | m-acc | mm-acc| |
|
| ------------ | ----- | ----- | |
|
| seed=42 | 84.30 | 84.98 | |
|
| seed=3407 (*)| 84.46 | 84.99 | |
|
| seed=54321 | 84.18 | 84.76 | |
|
| ------------ | ----- | ----- | |
|
| mean | 84.32 | 84.91 | |
|
| stdev | 0.140 | 0.133 | |
|
``` |
|
|
|
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} |
|
} |
|
``` |
