Create README.md

README.md

@@ -0,0 +1,27 @@
+# Model Description
+CompactBioBERT is a distilled version of the [BioBERT](https://huggingface.co/dmis-lab/biobert-base-cased-v1.2?text=The+goal+of+life+is+%5BMASK%5D.) model which is distilled for 100k training steps using a total batch size of 192 on the PubMed dataset. 
+
+# Distillation Procedure
+This model has the same overall architecture as [DistilBioBERT](https://huggingface.co/nlpie/distil-biobert), with the difference that here we combine the distillation approaches of DistilBioBERT and [TinyBioBERT](https://huggingface.co/nlpie/tiny-biobert). We utilise the same initialisation technique as in [DistilBioBERT](https://huggingface.co/nlpie/distil-biobert), and apply a layer-to-layer distillation with three major components, namely, MLM, layer, and output distillation.
+
+# Initialisation
+Following [DistilBERT](https://huggingface.co/distilbert-base-uncased?text=The+goal+of+life+is+%5BMASK%5D.), we initialise the student model by taking weights from every other layer of the teacher.
+
+# Architecture
+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.
+
+# Citation
+If you use this model, please consider citing the following paper:
+
+```bibtex
+@misc{https://doi.org/10.48550/arxiv.2209.03182,
+  doi = {10.48550/ARXIV.2209.03182},
+  url = {https://arxiv.org/abs/2209.03182},
+  author = {Rohanian, Omid and Nouriborji, Mohammadmahdi and Kouchaki, Samaneh and Clifton, David A.},
+  keywords = {Computation and Language (cs.CL), Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences, 68T50},
+  title = {On the Effectiveness of Compact Biomedical Transformers},
+  publisher = {arXiv},
+  year = {2022}, 
+  copyright = {arXiv.org perpetual, non-exclusive license}
+}
+```