Large language models, sometimes referred to as foundation models, have transformed multiple fields of research. However, smaller languages risk falling behind due to high training costs and small incentives for large companies to train these models. To combat this, the Danish Foundation Models project seeks to provide and maintain open, well-documented, and high-quality foundation models for the Danish language. This is achieved through broad cooperation with public and private institutions, to ensure high data quality and applicability of the trained models. We present the motivation of the project, the current status, and future perspectives.
@article{arxiv.2311.07264,
title = {Danish Foundation Models},
author = {Kenneth Enevoldsen and Lasse Hansen and Dan S. Nielsen and Rasmus A. F. Egebæk and Søren V. Holm and Martin C. Nielsen and Martin Bernstorff and Rasmus Larsen and Peter B. Jørgensen and Malte Højmark-Bertelsen and Peter B. Vahlstrup and Per Møldrup-Dalum and Kristoffer Nielbo},
journal= {arXiv preprint arXiv:2311.07264},
year = {2023}
}