Named after the Finnish word for reindeer, Poro is the first of a family of open-source multilingual LLMs.
Poro is a 34.2 billion parameter model, designed to process English, Finnish, and code.
Its been trained on a dataset of 1 trillion tokens.
It’s free, every week, in your inbox.
To achieve this, the team used a novel training approach, by pairing Finnish with high-resource languages.
It determined optimal data reuse frequencies for low-resource languages and integrated translated paired texts between Finnish and English.
Poro has also achieved another milestone: its the first multilingual model that has been trained on a EuroHPCsupercomputer.
Theyre also critical for EuropesAI sovereignty.
Poro is available for free under the Apache 2.0 License, which allows both commercial and research use.
One of the themes of this years TNW Conference is Ren-AI-ssance: The AI-Powered Rebirth.
Story byIoanna Lykiardopoulou
Ioanna is a writer at TNW.
With a background in the humanities, she has a soft spot for social impact-enabling technologies.
