s-nlp/roberta_first_toxicity_classifier

Toxicity Classification Model (but for the first part of the data)

This model is trained for toxicity classification task. The dataset used for training is the merge of the English parts of the three datasets by Jigsaw (Jigsaw 2018, Jigsaw 2019, Jigsaw 2020), containing around 2 million examples. We split it into two parts and fine-tune a RoBERTa model (RoBERTa: A Robustly Optimized BERT Pretraining Approach) on it. THIS MODEL WAS FINE-TUNED ON THE FIRST PART. The classifiers perform closely on the test set of the first Jigsaw competition, reaching the AUC-ROC of 0.98 and F1-score of 0.76.

How to use

from transformers import RobertaTokenizer, RobertaForSequenceClassification
# load tokenizer and model weights, but be careful, here we need to use auth token
tokenizer = RobertaTokenizer.from_pretrained('SkolkovoInstitute/roberta_toxicity_classifier', use_auth_token=True)
model = RobertaForSequenceClassification.from_pretrained('SkolkovoInstitute/roberta_toxicity_classifier', use_auth_token=True)
# prepare the input
batch = tokenizer.encode('you are amazing', return_tensors='pt')
# inference
model(batch)

Licensing Information

Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.