This biomedical language model uses a specialized biomedical tokenizer which is more closely aligned with human-morphological judgements than previous biomedical tokenizers such as PubMedBERT.

Details about our tokenizer design, pre-training procedure and downstream results can be found in our [BioNLP @ ACL 2023 paper](http://arxiv.org/pdf/2306.17649.pdf)

---
license: apache-2.0
---