https://github.com/aeovac/toxicity-model
Personnal training
https://github.com/aeovac/toxicity-model
ai classification python pytorch toxicity
Last synced: about 2 months ago
JSON representation
Personnal training
- Host: GitHub
- URL: https://github.com/aeovac/toxicity-model
- Owner: aeovac
- Created: 2025-04-19T16:41:54.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-04-20T08:44:12.000Z (about 1 year ago)
- Last Synced: 2025-04-20T09:46:49.928Z (about 1 year ago)
- Topics: ai, classification, python, pytorch, toxicity
- Language: Python
- Homepage:
- Size: 141 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Toxicity Classifier Model
A minimalist neural network for toxicity detection in text.
[Toxicity Dataset by Surge AI](https://github.com/surge-ai/toxicity/)
### Overview
This repo is a lightweight PyTorch-based model designed to classify text as toxic or non-toxic. It leverages a SentencePiece tokenizer and an LSTM-based architecture for efficient training on textual data.
Ensure you have Python 3.8+ and the required libraries installed:
```bash
pip install torch sentencepiece pandas scikit-learn numpy
```