DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation
Paper • 1911.00536 • Published • 2
# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("s-nlp/roberta_toxicity_classifier_v1")
model = AutoModelForSequenceClassification.from_pretrained("s-nlp/roberta_toxicity_classifier_v1")Quick Links
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
This model is a clone of SkolkovoInstitute/roberta_toxicity_classifier trained on a disjoint dataset.
While roberta_toxicity_classifier is used for evaluation of detoxification algorithms, roberta_toxicity_classifier_v1 can be used within these algorithms, as in the paper Text Detoxification using Large Pre-trained Neural Models.
- Downloads last month
- 41
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="s-nlp/roberta_toxicity_classifier_v1")