DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
Paper • 1910.01108 • Published • 23
Text Classification
Transformers
PyTorch
English
distilbert
toxic text classification
text-embeddings-inference
# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("tensor-trek/distilbert-toxicity-classifier")
model = AutoModelForSequenceClassification.from_pretrained("tensor-trek/distilbert-toxicity-classifier", device_map="auto")Quick Links
Toxicity Classification Model
This model is trained for toxicity classification task using. The dataset used for training is the dataset by Jigsaw ( Jigsaw 2020). We split it into two parts and fine-tune a DistilBERT model (DistilBERT base model (uncased) ) on it. DistilBERT is a distilled version of the BERT base model. It was introduced in this paper.
How to use
from transformers import pipeline
text = "This was a masterpiece. Not completely faithful to the books, but enthralling from beginning to end. Might be my favorite of the three."
classifier = pipeline("text-classification", model="tensor-trek/distilbert-toxicity-classifier")
classifier(text)
License
- Downloads last month
- 16
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="tensor-trek/distilbert-toxicity-classifier")