T

Toxic Comment Model

Developed by martin-ha
A toxic comment classification model fine-tuned on DistilBERT, used to identify harmful content in online comments
Downloads 238.97k
Release Time : 3/2/2022

Model Overview

This model is a specialized classifier for detecting toxic content in online comments, fine-tuned on the DistilBERT architecture, capable of identifying harmful speech in text.

Model Features

Efficient and lightweight
Based on the DistilBERT architecture, it reduces model size and computational requirements while maintaining high performance
Toxicity detection
Specially optimized for identifying harmful content in online comments
Fast inference
Trained in just 3 hours on a P100 GPU, suitable for real-time applications

Model Capabilities

Text classification
Toxic content detection
Natural language processing

Use Cases

Content moderation
Social media comment moderation
Automatically identify harmful comments on social media platforms
94% accuracy on test set
Forum content filtering
Help forum administrators filter inappropriate content
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase