Open Euro LLM
Extracto
A series of foundation models for transparent AI in Europe
Resumen
Resumen Principal
El proyecto OpenEuroLLM se establece como una iniciativa pionera y colaborativa que reúne a las principales empresas e instituciones de investigación europeas en IA para desarrollar una serie de modelos fundacionales de lenguaje (LLMs) transparentes y de alto rendimiento. Este esfuerzo ambicioso se cimenta en la premisa de una apertura radical, abarcando desde los datos y la documentación hasta el
Contenido
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
GOALS TOWARDS PERFORMANT AND TRANSPARENT AI
Extend the multilingual capabilities of existing 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.
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