# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("Arsive/roberta-toxicity-classifier")
model = AutoModelForSequenceClassification.from_pretrained("Arsive/roberta-toxicity-classifier")Quick Links
Roberta-base model trained on Arsive/toxicity_classification_jigsaw
The following are the corresponding labels:
LABEL_0: toxic
LABEL_1: severe_toxic
LABEL_2: obscene
LABEL_3: threat
LABEL_4: insult
LABEL_5: identity_hate
- Downloads last month
- 11
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Arsive/roberta-toxicity-classifier")