|
--- |
|
title: README |
|
emoji: 🏃 |
|
colorFrom: gray |
|
colorTo: purple |
|
sdk: static |
|
pinned: false |
|
license: mit |
|
--- |
|
|
|
# Model Description |
|
BioMobileBERT is the result of training the [MobileBERT-uncased](https://huggingface.co/google/mobilebert-uncased) model in a continual learning scenario for 200k training steps using a total batch size of 192 on the PubMed dataset. |
|
|
|
# Initialisation |
|
We initialise our model with the pre-trained checkpoints of the [MobileBERT-uncased](https://huggingface.co/google/mobilebert-uncased) model available on Huggingface. |
|
|
|
# Architecture |
|
MobileBERT uses a 128-dimensional embedding layer followed by 1D convolutions to up-project its output to the desired hidden dimension expected by the transformer blocks. For each of these blocks, MobileBERT uses linear down-projection at the beginning of the transformer block and up-projection at its end, followed by a residual connection originating from the input of the block before down-projection. Because of these linear projections, MobileBERT can reduce the hidden size and hence the computational cost of multi-head attention and feed-forward blocks. This model additionally incorporates up to four feed-forward blocks in order to enhance its representation learning capabilities. Thanks to the strategically placed linear projections, a 24-layer MobileBERT (which is used in this work) has around 25M parameters. |
|
|
|
# Citation |
|
If you use this model, please consider citing the following paper: |
|
|
|
```bibtex |
|
@article{rohanian2023effectiveness, |
|
title={On the effectiveness of compact biomedical transformers}, |
|
author={Rohanian, Omid and Nouriborji, Mohammadmahdi and Kouchaki, Samaneh and Clifton, David A}, |
|
journal={Bioinformatics}, |
|
volume={39}, |
|
number={3}, |
|
pages={btad103}, |
|
year={2023}, |
|
publisher={Oxford University Press} |
|
} |
|
``` |
