---
language:
- ru
tags:
- Transformers
- bert
pipeline_tag: fill-mask
thumbnail: https://github.com/sberbank-ai/model-zoo
license: apache-2.0
widget:
- text: Применение метода <mask> векторов для решения задач классификации
---

# ruSciBERT
Model was trained by Sber AI team and MLSA Lab of Institute for AI, MSU.
If you use our model for your project, please tell us about it ([nikgerasimenko@gmail.com](nikgerasimenko@gmail.com)).


[Presentation at the AI Journey 2022](https://ai-journey.ru/archive/?year=2022&video=https://vk.com/video_ext.phpq3u4e5st6io8nm7a0rkoid=-22522055a2n3did=456242496a2n3dhash=ae9efe06acf647fd)
* Task: `mask filling`
* Type: `encoder`
* Tokenizer: `bpe`
* Dict size: `50265`
* Num Parameters: `123 M`
* Training Data Volume: `6.5 GB`