# Multilingual information retrieval

This is a sentence transformer model based on ModernBERT-base, specifically designed for calculating sentence similarity and information retrieval tasks.

This is an instruction-following model specifically optimized for Russian, based on the Vikhr Base architecture, trained on various instruction datasets using curriculum learning.

This is an Italian sentence embedding model based on sentence-transformers, capable of mapping sentences and paragraphs into a 384-dimensional dense vector space, suitable for tasks such as semantic search and sentence similarity calculation.

Italian sentence embedding model based on sentence-transformers, mapping text to a 768-dimensional vector space, suitable for semantic search and clustering tasks