Your summer read by Keith and Knut

We asked two leading researchers at the Department of Computer Science at NTNU for their summer read recommendations. Professor Keith Downing and Associate Professor Knut Magne Risvik were not difficult to ask, and they both put together a list in several formats with some brief comments on their choices.

2024-06-27

NorwAI has since 2021 worked to develop large language models based on Norwegian data. NorwAI has built four test models that are steppingstones to build a super large Norwegian foundation model. 

In 2024, NorwAI’s language modeling efforts will diverge into two distinct tracks. There is a need to train a Norwegian generative model that is sufficiently large to support the Norwegian language at the same level as English and other major languages supported by international models. Simultaneously, there is a demand for smaller models that can be easily optimized for specific use cases and controlled locally using proprietary data and custom adaptations. 
The smaller models will be launched in Oslo on May 15th. 

What have NorwAI learned from its work on language models? The path for NorLLM is described in our new section:  key learning, lessons learned, observations, on privacy, hurtful examples, and other articles in our guide to NorLLM. 

Visit our webpages in English and Norwegian, dedicated to NorLLM:

NorLLM English version

NorLLM Norsk versjon