|
--- |
|
language: en |
|
thumbnail: https://huggingface.co/front/thumbnails/microsoft.png |
|
tags: |
|
- text-classification |
|
license: mit |
|
--- |
|
|
|
# XtremeDistil-Transformers for Distilling Massive Neural Networks |
|
|
|
XtremeDistil is a distilled task-agnostic transformer model leveraging multi-task distillation techniques from the paper "[XtremeDistil: Multi-stage Distillation for Massive Multilingual Models](https://www.aclweb.org/anthology/2020.acl-main.202.pdf)" and "[MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://arxiv.org/abs/2002.10957)" with the following "[Github code](https://github.com/microsoft/xtreme-distil-transformers)". |
|
|
|
This l6-h384 checkpoint with **6** layers, **384** hidden size, **12** attention heads corresponds to **22 million** parameters with **5.3x** speedup over BERT-base. |
|
|
|
The following table shows the results on GLUE dev set and SQuAD-v2. |
|
|
|
| Models | #Params | Speedup | MNLI | QNLI | QQP | RTE | SST | MRPC | SQUAD2 | Avg | |
|
|----------------|--------|---------|------|------|------|------|------|------|--------|-------| |
|
| BERT | 109 | 1x | 84.5 | 91.7 | 91.3 | 68.6 | 93.2 | 87.3 | 76.8 | 84.8 | |
|
| DistilBERT | 66 | 2x | 82.2 | 89.2 | 88.5 | 59.9 | 91.3 | 87.5 | 70.7 | 81.3 | |
|
| TinyBERT | 66 | 2x | 83.5 | 90.5 | 90.6 | 72.2 | 91.6 | 88.4 | 73.1 | 84.3 | |
|
| MiniLM | 66 | 2x | 84.0 | 91.0 | 91.0 | 71.5 | 92.0 | 88.4 | 76.4 | 84.9 | |
|
| MiniLM | 22 | 5.3x | 82.8 | 90.3 | 90.6 | 68.9 | 91.3 | 86.6 | 72.9 | 83.3 | |
|
| XtremeDistil | 22 | 5.3x | 85.4 | 90.3 | 91.0 | 80.9 | 92.3 | 90.0 | 76.6 | 86.6 | |
|
|
|
Tested with `tensorflow 2.3.1, transformers 4.1.1, torch 1.6.0` |
|
|
|
If you use this checkpoint in your work, please cite: |
|
|
|
``` latex |
|
@inproceedings{mukherjee-hassan-awadallah-2020-xtremedistil, |
|
title = "{X}treme{D}istil: Multi-stage Distillation for Massive Multilingual Models", |
|
author = "Mukherjee, Subhabrata and |
|
Hassan Awadallah, Ahmed", |
|
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics", |
|
month = jul, |
|
year = "2020", |
|
address = "Online", |
|
publisher = "Association for Computational Linguistics", |
|
url = "https://www.aclweb.org/anthology/2020.acl-main.202", |
|
doi = "10.18653/v1/2020.acl-main.202", |
|
pages = "2221--2234", |
|
} |
|
``` |
|
|
|
``` latex |
|
@misc{wang2020minilm, |
|
title={MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers}, |
|
author={Wenhui Wang and Furu Wei and Li Dong and Hangbo Bao and Nan Yang and Ming Zhou}, |
|
year={2020}, |
|
eprint={2002.10957}, |
|
archivePrefix={arXiv}, |
|
primaryClass={cs.CL} |
|
} |
|
``` |
|
|
