A tiny Russian BERT-based model fine-tuned for sentence similarity and semantic embeddings. It produces 312-dimensional vectors that can be used for clustering, semantic search, and paraphrase detection. The model is optimized for speed and low resource usage while delivering strong performance on Russian language tasks.
In the Foundation models & chat space, Rubert Tiny2 takes a focused approach. It focuses on computing high-quality Russian text embeddings with a small, fast model suitable for production use. Rubert Tiny2 is an open-source project aimed at developers. The project is open source (Open Source). It runs on the web, the command line, and API.
It is developed by cointegrated, and the product first shipped in 2022. Among its 3 catalogued features are sentence embeddings, semantic similarity, and lightweight model.
Latest indexed changes and source events
cointegrated/rubert-tiny2 verified by the PulseGate indexer
Other apps tracked under the same category.
