Ruscibert
A Russian BERT model jointly trained by Sber AI team and MLSA Lab at Moscow State University's AI Institute, specializing in scientific text processing
Downloads 1,044
Release Time : 12/21/2022
Model Overview
A Russian pre-trained language model based on BERT architecture, specifically optimized for scientific texts, suitable for masked filling tasks
Model Features
Scientific text optimization
Specifically trained and optimized for Russian scientific texts
Large-scale training data
Trained using 6.5GB of Russian text data
Efficient tokenization
Uses BPE algorithm tokenizer with a vocabulary size of 50,265 tokens
Model Capabilities
Russian text understanding
Scientific text processing
Masked word prediction
Use Cases
Natural Language Processing
Scientific text classification
Classification tasks for Russian scientific literature
Vector method applications
Using model-generated text vectors to solve classification problems
Featured Recommended AI Models
Š 2025AIbase