AI RESEARCH

Soro: A Lightweight Foundation Model and Chatbot for Tajik

arXiv CS.AI

ArXi:2605.27379v1 Announce Type: new We present Soro, a family of Tajik-specialized conversational large language models (LLMs) designed for real-world deployment under tight compute and connectivity constraints in Tajikistan. Starting from open-weight Gemma 3 checkpoints, we perform Tajik-only continual pre