DanBERT
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 millions, danish words. The training has been conducted as part of a thesis.
The model can be found at:
Intended uses & limitations
How to use
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("alexanderfalk/danbert-small-cased")
model = AutoModel.from_pretrained("alexanderfalk/danbert-small-cased")
BibTeX entry and citation info
@inproceedings{...,
year={2020},
title={Anonymization of Danish, Real-Time Data, and Personalized Modelling},
author={Alexander Falk},
}