Vikhrmodels/Vikhr-Gemma-2B-instruct

Vikhr-Gemma-2B-instruct is a 2.6 billion parameter instruction-tuned language model developed by Vikhrmodels, based on the Gemma 2 2B architecture. It is specifically trained on the Russian-language GrandMaster-PRO-MAX dataset, making it highly specialized for processing and generating text in Russian. This compact model excels at Russian language tasks, offering a powerful solution for applications requiring strong performance in this domain.