AI-Sweden-Models/gpt-sw3-356m-instruct

The AI-Sweden-Models/gpt-sw3-356m-instruct is a 0.5 billion parameter, instruction-tuned decoder-only transformer language model developed by AI Sweden in collaboration with RISE and WASP WARA for Media and Language. It is part of the GPT-SW3 collection, trained on 320 billion tokens across Swedish, Norwegian, Danish, Icelandic, English, and programming code, with a context length of 2048 tokens. This model is specifically fine-tuned on instruction data for generating coherent text and performing various text tasks in five languages and four programming languages.