Vör and Norn
Icelandic language models, trained on my own machine and a borrowed DGX Spark
Norn inflects Icelandic correctly and Vör finds personal data in Icelandic documents. Both models are open on Hugging Face.
Norn is a series of Icelandic language models I train on Hercules, my own machine, and on a DGX Spark I borrowed for testing. The fourth version is built on Gemma 4 with 31 billion parameters and inflects Icelandic words correctly 86% of the time on a test drawn from the Database of Icelandic Morphology. The base model gets 70%.
Vör is its specialised sibling. It reads Icelandic documents and labels every item of personal data under Act no. 90/2018 on data protection, whether a name, a kennitala, a health condition or a criminal record. On 317 test documents it found 98.7% of all items. The test documents are synthetic, and real documents are the next test.
Both models are open on Hugging Face: Vör and Norn v4. More in the blog post.
Technology Stack
Related Projects
View all projects →
BORG
The University of Akureyri's hybrid AI platform, combining commercial models with on-premise infrastructure so sensitive data stays on the university network.
Smarason.is
A personal site moved home: Next.js 16 + Payload on its own Hetzner edge with Caddy, no cloud content service, zero tracking. The architecture is the philosophy — sovereignty over your own data.
Institutional Knowledge Graph
Small organisations run on invisible architecture — governance, systems, policies, dependencies that live in people’s heads. This is the complete methodology for making that architecture queryable: Neo4j, JSON-LD, SHACL, and a pipeline that is always safe to re-run.