Helsinki-based Silo AI has completed the training of the Poro model — a new milestone in its mission to create large language models (LLMs) for low-resource languages. Named after the Finnish word for “reindeer,” Poro is the first of a family of open-source multilingual LLMs. The startup is building the models alongside the University of Turku and the EU’s High Performance Language Technologies (HPLT) project. Poro is a 34.2 billion parameter model, designed to process English, Finnish, and code. It’s been trained on a dataset of 1 trillion tokens. “What we are proving with Poro is that we can build…
This story continues at The Next Web