CompactBioBERT is a distilled version of the
BioBERT model which is distilled for 100k training steps using a total batch size of 192 on the PubMed dataset.
This model has the same overall architecture as
DistilBioBERT with the difference that here we combine the distillation approaches of DistilBioBERT and
TinyBioBERT. We utilise the same initialisation technique as in
DistilBioBERT, and apply a layer-to-layer distillation with three major components, namely, MLM, layer, and output distillation.
Following
DistilBERT, we initialise the student model by taking weights from every other layer of the teacher.
In this model, the size of the hidden dimension and the embedding layer are both set to 768. The vocabulary size is 28996. The number of transformer layers is 6 and the expansion rate of the feed-forward layer is 4. Overall, this model has around 65 million parameters.
1@article{rohanian2023effectiveness,
2 title={On the effectiveness of compact biomedical transformers},
3 author={Rohanian, Omid and Nouriborji, Mohammadmahdi and Kouchaki, Samaneh and Clifton, David A},
4 journal={Bioinformatics},
5 volume={39},
6 number={3},
7 pages={btad103},
8 year={2023},
9 publisher={Oxford University Press}
10}
If this model helps your work, you can keep the project running with a one-off or monthly contribution:
https://github.com/sponsors/nlpie-research
