Danbert Small Cased

🚀 DanBERT

DanBERT is a Danish pre - trained model based on BERT - Base. It has been trained on over 2 million sentences and 40 million Danish words as part of a thesis. This model offers capabilities in named entity recognition and token criticality analysis.

🚀 Quick Start

How to use

from transformers import AutoTokenizer, AutoModel  
tokenizer = AutoTokenizer.from_pretrained("alexanderfalk/danbert-small-cased")  
model = AutoModel.from_pretrained("alexanderfalk/danbert-small-cased") 

✨ Features

• Named Entity Recognition: Capable of identifying named entities in Danish text.
• Token Criticality Analysis: Can analyze the criticality of tokens in the text.

📦 Installation

No specific installation steps provided in the original document.

📚 Documentation

Model description

DanBERT is a Danish pre - trained model based on BERT - Base. The pre - trained model has been trained on more than 2 million sentences and 40 million Danish words. The training has been conducted as part of a thesis. The model can be found at:

• danbert - da

Intended uses & limitations

The model is designed for tasks related to Danish text processing such as named entity recognition and token criticality analysis. However, specific limitations are not detailed in the original document.

BibTeX entry and citation info

@inproceedings{...,
  year={2020},
  title={Anonymization of Danish, Real - Time Data, and Personalized Modelling},
  author={Alexander Falk},
}

📄 License

This project is licensed under the Apache - 2.0 license.