Bert-based classifier (finetuned from Conversational Rubert ) trained on merge of Russian Language Toxic Comments dataset collected from 2ch.hk and Toxic Russian Comments dataset collected from ok.ru.

The datasets were merged, shuffled, and split into train, dev, test splits in 80-10-10 proportion. The metrics obtained from test dataset is as follows

How to use

from transformers import BertTokenizer, BertForSequenceClassification

# load tokenizer and model weights
tokenizer = BertTokenizer.from_pretrained('SkolkovoInstitute/russian_toxicity_classifier')
model = BertForSequenceClassification.from_pretrained('SkolkovoInstitute/russian_toxicity_classifier')

# prepare the input
batch = tokenizer.encode('ты супер', return_tensors='pt')

# inference
model(batch)

Licensing Information

Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License .