LionGuard

LionGuard is a classifier for detecting unsafe content in the Singapore context. It uses pre-trained BAAI English embeddings and performs classification with a trained Ridge Classification model.

Usage

Install transformers , onnxruntime and huggingface_hub libraries.

pip install transformers onnxruntime huggingface_hub

Run inference.

python inference.py '["Example text 1"]'

Technical report is available here.

Downloads last month: 28

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Spaces using govtech/lionguard-v1 6

Collection including govtech/lionguard-v1

LionGuard 🦁

Collection

A Singapore-contextualized moderation classifier. • 2 items • Updated Jul 28, 2025 • 1

Paper for govtech/lionguard-v1

LionGuard: Building a Contextualized Moderation Classifier to Tackle Localized Unsafe Content

Paper • 2407.10995 • Published Jun 24, 2024 • 2