| # oBERT-12-upstream-pruned-unstructured-97-finetuned-qqp | |
| 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 2 - oBERT - QQP 97%`. | |
| ``` | |
| Pruning method: oBERT upstream unstructured + sparse-transfer to downstream | |
| Paper: https://arxiv.org/abs/2203.07259 | |
| Dataset: QQP | |
| Sparsity: 97% | |
| 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 97% | acc | F1 | | |
| | ------------ | ----- | ----- | | |
| | seed=42 (*)| 89.85 | 86.41 | | |
| | seed=3407 | 89.72 | 86.42 | | |
| | seed=54321 | 89.70 | 86.24 | | |
| | ------------ | ----- | ----- | | |
| | mean | 89.76 | 86.35 | | |
| | stdev | 0.081 | 0.101 | | |
| ``` | |
| Code: _coming soon_ | |
| ## BibTeX entry and 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} | |
| } | |
| ``` |