OpenEuroLLM at Cyber Valley Day
Cyber Valley Innovation Campus
Our colleagues from ELLIS Institute Tübingen and Tübingen AI Center were presenting the OpenEuroLLM project at the Cyber Valley Innovation Campus 10th anniversary at Tübingen
A series of foundation models for transparent AI in Europe
truly open
including data, documentation, training and testing code, and evaluation metrics; including community involvement
compliant
under EU regulations, OpenEuroLLM will provide a series of transparent and performant LLMs
diverse
for European languages and other socially and economically interesting ones, preserving linguistic and cultural diversity
Updates
Events
International Workshop on Open Source Sovereign Foundation Models.
Presenting the OpenEuroLLM project in OSFM
Our colleague from the University of Oslo, Stephan Oepen, presented the OpenEuroLLM project goals and current status at the 2nd International Workshop on Open Source Sovereign Foundation Models (OSFM), which brought together experts to discuss strategies for promoting AI innovation and digital sovereignty in Europe through open and transparent models.
SURF Research Day 2026
How to build and use sovereign LLM?
Our colleagues from SURF invited Diana Onutu to the SURF Research Day to participate on behalf of OpenEuroLLM in a panel discussion aiming at connecting researchers, startups, and policymakers interested in developing national European sovereign LLMs and their responsible deployment.
Language Resources and Evaluation Conference (LREC)
Meet OpenEuroLLM at LREC 2026
OpenEuroLLM is giving full support to the LREC 2026 conference through a sponsorship, several presentations and a booth in the exhibitors hall for 3 days. We will be happy to talk to you during the main conference days in person!
Gothenburg Artificial Intelligence Alliance (GAIA) Conference
OpenEuroLLM to be presented at GAIA Conference 2026
Jonas Lind, Head of Research for the NLU team at AI Sweden, partner in OpenEuroLLM, will unpack the reality of R&D for the continental operation that our project represents.
Multilinguality in LLM Development and Evaluation.
First OpenEuroLLM 2026 Winter School
Last February, in collaboration with the Circle U Alliance and the Nordic Language Processing Laboratory, the first OpenEuroLLM Winter School took place in the Norwegian Mountains. The focus of this year was Multilinguality in LLM Development and Evaluation with speakers from world organisations, academia and industry.
Goals towards performant and transparent AI
Develop strong multilingual foundation models for EU official languages and beyond.
Ensure easy and sustainable access to foundational models ready to be fine-tuned to a wide range of applications.
Extend the number of evaluation results in all EU official languages and beyond, including AI safety and alignment with the AI Act and European AI standards
Extend the number of available training datasets and benchmarks for these languages, and make them easily accessible.
Share transparently the tools, recipes and intermediate results of the training processes.
Share the dataset enrichment and anonymization pipelines to enable further data sourcing for future needs.
Create an active and engaged community of developers and stakeholders among the public and private sector.
FAQ
Frequently asked questions
Find answers about OpenEuroLLM code, data, models, releases, research progress and multilingual coverage.
01Where is the code?
The code we wrote is available in https://github.com/OpenEuroLLM In particular,
- training data catalogue: https://github.com/OpenEuroLLM/training-data-catalogue/blob/main/README.md
- pretraining code: OpenEuroLLM/oellm-autoexp : Merge of megatron-train, autoexperiment and oellm_pretrain.
- post-training code: https://github.com/OpenEuroLLM/post-training
- evaluation scheduling: https://github.com/OpenEuroLLM/oellm-eval
- LLM judge evaluations: https://github.com/OpenEuroLLM/JudgeArena
02Where is the data?
03Where are the current models? How do they perform?
PARTNERS IN OPENEUROLLM
Europe's leading AI companies and research institutions combine their forces and expertise to develop next-generation open-source language models in an unprecedented collaboration to advance European AI capabilities, the OpenEuroLLM project
Universities and Research Organizations
Companies
HPC Centres
