distilbert-base-uncased__hate_speech_offensive__train-16-2 Open Source Model - Lightweight Detection of Hateful and Offensive Text Content

Distilbert Base Uncased Hate Speech Offensive Train 16 2

Developed by SetFit

A lightweight model based on DistilBERT for detecting hate speech and offensive content in text

Downloads 18

Release Time : 3/2/2022

Model Overview

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

Lightweight and Efficient

Based on the DistilBERT architecture, it is smaller and faster than standard BERT models while maintaining good performance.

Hate Speech Detection

Text classification capability specifically optimized for hate speech and offensive content.

Text classification

Hate speech recognition

Offensive content detection

Content moderation

Social media content filtering

Automatically identify and flag hate speech and offensive content on social media.

Online community management

Help administrators quickly detect and handle inappropriate comments.

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.0915	1.0	10	1.1051	0.4
1.0663	2.0	20	1.0794	0.3
1.0307	3.0	30	1.0664	0.5
0.9443	4.0	40	1.0729	0.5
0.8373	5.0	50	1.0175	0.4
0.6892	6.0	60	0.9624	0.5
0.538	7.0	70	0.9924	0.5
0.4173	8.0	80	1.0136	0.6
0.1846	9.0	90	1.0683	0.6
0.1125	10.0	100	1.2376	0.6
0.0754	11.0	110	1.2537	0.6
0.0401	12.0	120	1.4387	0.6
0.0285	13.0	130	1.5702	0.6
0.0241	14.0	140	1.6795	0.6
0.0175	15.0	150	1.7228	0.6
0.0147	16.0	160	1.7892	0.6

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base