Edit model card

German Medical BERT

This is a fine-tuned model on the Medical domain for the German language and based on German BERT. This model has only been trained to improve on-target tasks (Masked Language Model). It can later be used to perform a downstream task of your needs, while I performed it for the NTS-ICD-10 text classification task.


Language model: bert-base-german-cased

Language: German

Fine-tuning: Medical articles (diseases, symptoms, therapies, etc..)

Eval data: NTS-ICD-10 dataset (Classification)

Infrastructure: Google Colab


  • We fine-tuned using Pytorch with Huggingface library on Colab GPU.
  • With standard parameter settings for fine-tuning as mentioned in the original BERT paper.
  • Although had to train for up to 25 epochs for classification.

Performance (Micro precision, recall, and f1 score for multilabel code classification)

Models P R F1
German BERT 86.04 75.82 80.60
German MedBERT-256 (fine-tuned) 87.41 77.97 82.42
German MedBERT-512 (fine-tuned) 87.75 78.26 82.73


Manjil Shrestha: shresthamanjil21 [at] gmail.com

Related Paper: Report

Get in touch: LinkedIn

Downloads last month
Hosted inference API
Mask token: [MASK]
This model can be loaded on the Inference API on-demand.