Small open multilingual models: prompt injection, PII, content safety, hallucination, zero-shot, language detection. Apache-2.0, ONNX.
-
Horizon-Labs/prompt-injection-guard-base
Text Classification • 0.3B • Updated • 396 -
Horizon-Labs/prompt-injection-guard-small
Text Classification • 0.1B • Updated • 332 -
Prompt Injection Guard
🛡Detect prompt injection in your browser (transformers.js)
-
Horizon-Labs/pii-redactor-base
Token Classification • 0.3B • Updated • 83