# Scientific Text Embedding

SciRus-tiny is a compact model for obtaining Russian and English scientific text embeddings, trained on eLibrary data using contrastive learning techniques.

A sentence embedding model based on sentence-transformers, specifically optimized for biomedical literature, capable of mapping text to a 384-dimensional vector space

A model based on SciBERT, fine-tuned with SNLI and MultiNLI datasets, for generating universal sentence embeddings

SciBERT-based scientific text sentence encoder, trained on 2 million scientific papers through self-supervised learning

A model based on sentence-transformers that maps sentences and paragraphs into a 768-dimensional dense vector space, suitable for tasks such as clustering or semantic search.