nlpie/tiny-clinicalbert

1---2title: README3emoji: 🏃4colorFrom: gray5colorTo: purple6sdk: static7pinned: false8license: mit9tags:10- oxford-legacy11---12 13# Model Description14TinyClinicalBERT is a distilled version of the [BioClinicalBERT](https://huggingface.co/emilyalsentzer/Bio_ClinicalBERT) which is distilled for 3 epochs using a total batch size of 192 on the MIMIC-III notes dataset.15 16# Distillation Procedure17This model uses a unique distillation method called ‘transformer-layer distillation’ which is applied on each layer of the student to align the attention maps and the hidden states of the student with those of the teacher.18 19# Architecture and Initialisation20This model uses 4 hidden layers with a hidden dimension size and an embedding size of 768 resulting in a total of 15M parameters. Due to the model's small hidden dimension size, it uses random initialisation.21 22# Citation23 24If you use this model, please consider citing the following paper:25 26```bibtex27@article{rohanian2023lightweight,28  title={Lightweight transformers for clinical natural language processing},29  author={Rohanian, Omid and Nouriborji, Mohammadmahdi and Jauncey, Hannah and Kouchaki, Samaneh and Nooralahzadeh, Farhad and Clifton, Lei and Merson, Laura and Clifton, David A and ISARIC Clinical Characterisation Group and others},30  journal={Natural Language Engineering},31  pages={1--28},32  year={2023},33  publisher={Cambridge University Press}34}35```36 37# Support38If this model helps your work, you can keep the project running with a one-off or monthly contribution:  39https://github.com/sponsors/nlpie-research