minilingua-ai

Welcome to the MiniLingua-AI Hub

This organization is a space curated by Anna Aksenova and Boris Zverkov as part of their thesis project focused on the development of a multilingual small language model and the open datasets used for its training.

📚 Project Highlights:

• Development of a 1B parameter multilingual LLM
• Custom tokenizer supporting 13 languages and code
• Instruction fine-tuning and multilingual evaluation
• Open, reproducible training datasets and resources

This hub includes both model checkpoints and datasets related to MiniLingua, aiming to support research in inclusive language modeling for European languages.

Stay tuned for more 🌐✨