distilbert-base-uncased Open Source Model - Free Deployment for Detecting Hate and Offensive Language

Home

Distilbert Base Uncased Hate Speech Offensive Train 32 6

Developed by SetFit

A lightweight model based on DistilBERT, fine-tuned for hate speech and offensive language detection tasks

Text Classification

Transformers

Open Source License:Apache-2.0 #Hate speech detection #Lightweight BERT #Text classification

Downloads 17

Release Time : 3/2/2022

Model Overview

This model is a fine-tuned version of the DistilBERT base model, specifically designed to detect hate speech and offensive content in text.

Model Features

Lightweight and efficient

Based on the DistilBERT architecture, it is 40% smaller than the standard BERT model while retaining 95% of its performance.

Hate speech detection

Specifically optimized for identifying hate speech and offensive content in text.

Fast inference

The distilled architecture enables faster model inference, making it suitable for real-time applications.

Model Capabilities

Text classification

Hate speech detection

Offensive language identification

Use Cases

Content moderation

Social media content filtering

Automatically detect and filter hate speech and offensive content on social media platforms

Achieved 66.3% accuracy on the evaluation dataset

Online community management

Assist forums and online communities in identifying inappropriate speech

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.0957	1.0	19	1.0696	0.6
1.0107	2.0	38	1.0047	0.55
0.8257	3.0	57	0.8358	0.8
0.6006	4.0	76	0.7641	0.6
0.4172	5.0	95	0.5931	0.8
0.2639	6.0	114	0.5570	0.7
0.1314	7.0	133	0.5017	0.65
0.0503	8.0	152	0.3115	0.75
0.023	9.0	171	0.4353	0.85
0.0128	10.0	190	0.5461	0.75
0.0092	11.0	209	0.5045	0.8
0.007	12.0	228	0.5014	0.8
0.0064	13.0	247	0.5070	0.8
0.0049	14.0	266	0.4681	0.8
0.0044	15.0	285	0.4701	0.8
0.0039	16.0	304	0.4862	0.8
0.0036	17.0	323	0.4742	0.8
0.0035	18.0	342	0.4652	0.8

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご

Distilbert Base Uncased Hate Speech Offensive Train 32 6

Model Overview

Model Features

Model Capabilities

Use Cases

🚀 distilbert-base-uncased__hate_speech_offensive__train-32-6

🚀 Quick Start

📚 Documentation

Model description

Intended uses & limitations

Training and evaluation data

🔧 Technical Details

Training procedure

Training hyperparameters

Training results

Framework versions

📄 License