FLEXI - FernUni LLM Experimental Infrastructure
Photo: Yuchiro Chino/Getty Images
The FLEXI (FernUniversität LLM Experimental Infrastructure) project at FernUniversität in Hagen is providing an open infrastructure for large language models (LLMs). Its aim is to facilitate innovative experiments and research in higher education, as well as evaluating the benefits of locally operated, open LLMs compared to commercial cloud services.
FLEXI offers maximum data protection, as all data remains within the university's IT infrastructure. The platform supports various use cases such as chatbots, retrieval-augmented generation (RAG), API access, and Moodle integration, enabling a wide range of applications in teaching and research. The project is continuously being developed and provides valuable insights into scaling, maintenance, and the legal framework for university-wide operation of open AI systems.
News article: FLEXI - Guidance on the local hosting of LLMs
How to deal with AI in university teaching? Which access points should universities provide for teachers and students? As part of the FernUni LLM Experimental Infrastructure (FLEXI) project, Torsten Zesch and an interdisciplinary team are dedicated to testing and using a locally hosted open Large Language Model (LLM).
-
- Zesch, T., Hanses, M., Seidel, N., Aggarwal, P., Veiel, D., & de Witt, C. (2024). Flexible LLM Experimental Infrastructure (Flexi) – Enabling Experimentation and Innovation in Higher Education Through Access to Open LLMs. In 2024 21st International Conference on Information Technology Based Higher Education and Training (ITHET) (pp. 1–8). IEEE.https://doi.org/10.1109/ITHET61869.2024.10837635
-
