A sovereign Norwegian base model with 3 billion parameters – trained from scratch, built for European jurisdiction.
A Norwegian base model (LLM) trained from scratch on Norwegian and Nordic data – designed for further specialisation through fine-tuning, RAG and agents.
Pre-training complete – final polishing (anneal) in progress.
Od1n V5 forms the basis for customer-specific, fine-tuned models. See Technology for the full benchmark and methodology, or how Od1n is built.
Talk to us about how a sovereign Norwegian language model can be adapted to your organisation.
Contact usSee the benchmark