DeepPavlov/rubert-base-cased-sentence

Sentence RuBERT is a representation‑based sentence encoder for Russian . It is fine‑tuned on SNLI[1] google-translated to russian and on russian part of XNLI dev set[2] Sentence representations are mean pooled token embeddings in the same manner as in Sentence‑BERT[3]. It is an annotated corpus for learning natural language inference . It's been used in the past to learn how to use sentence-based sentences in Russian . The code is based on the language of the Russian language . It has been used to generate a large corpus for natural language learning . It was created by the Russian-language-,