The cjvt/GaMS-2B-Instruct model is a 2 billion parameter instruction-tuned language model developed by researchers at the University of Ljubljana, Faculty for Computer and Information Science. Based on Google's Gemma 2 architecture, it has been continually pretrained on Slovene, English, Croatian, Bosnian, and Serbian corpora. This model is specifically fine-tuned for instruction following and excels in multilingual contexts, particularly for tasks involving Slovene and related South Slavic languages.
No reviews yet. Be the first to review!
Hugging Face