Vikhrmodels/Vikhr-Llama-3.2-1B-Instruct

Vikhr-Llama-3.2-1B-Instruct is a 1 billion parameter instruction-tuned causal language model developed by Vikhrmodels, based on Llama-3.2-1B-Instruct. Specialized for the Russian language, it was trained on the GrandMaster-PRO-MAX dataset and offers 5x efficiency compared to its base model. With a 32768 token context length, this compact model is optimized for deployment on low-power and mobile devices.