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.
Rubert Tiny2 sits in PulseGate's Embeddings & retrieval category. 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. Rubert Tiny2 is open source under the Open Source license. It ships for the web, the command line, and API.
cointegrated builds and maintains Rubert Tiny2, and it first shipped in 2022. Key capabilities include sentence embeddings, semantic similarity, and lightweight model.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do