Skip to main content Skip to main navigation

Project | soofi

Duration:
Sovereign Open Source Foundation Models

Sovereign Open Source Foundation Models

We are developing a larger AI language model that will be made available to the economy and society as open source. Based on a large language model (LLM), a so-called reasoning model will also be created using special procedures to increase the quality of the overall system and optimise resource consumption. In addition, initial use cases are to be implemented using AI agent technologies.

Partners

KI Bundesverband

Universität Bonn

Technische Universität Darmstadt

Julius-Maximilians-Universität Würzburg

Berliner Hochschule für Technik

Merantix Momentum

Fraunhofer IAIS

LAMARR

Leibniz Universität Hannover

Ellamind

Publications

  1. FineWeb-CLaR: Culture, Language, and Region Annotations for Benchmark-Aligned Corpus Auditing

    Yusser Al Ghussin; Eva Morgan Toulouse Gavaller; Cristina España-Bonet; Josef van Genabith; Simon Ostermann

    In: Hung-Yi Lee; Sunipa Dev; Junyi Jessy Li; Desmond Elliott (Hrsg.). Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing. Conference on Empirical Methods in Natural Language Processing (EMNLP), Budapest, Hungary, Pages 50417-50445, ISBN 979-8-89176-459-0, Association for Computational Linguistics, 2026.

Funding Authorities

BMWE - Federal Ministry for Economic Affairs and Energy

BMWE - Federal Ministry for Economic Affairs and Energy