TangoBeeAkto/deberta-prompt-injection-v2
By TangoBeeAkto · ↓ 3 · ♥ 0 · Updated 2025-11-30
What's in this repo
This page lists the files in TangoBeeAkto/deberta-prompt-injection-v2, including model.onnx.
- 1 ONNX models (.onnx files)
- 18 files, including 10 .json, 2 .model, 1 .md, 1 .csv, 1 .safetensors, 1 .onnx
- Last updated 2025-11-30
ONNX files
| File | Size | Download |
|---|---|---|
| onnx/model.onnx | — | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
deberta-prompt-injection-v2
This is an ONNX model used by LLM Guard for security scanning of Large Language Models.
Model Details
Base Model: microsoft/deberta-v3-base (fine-tuned)
This model has been converted to ONNX format for optimized inference performance.
Usage
This model is used automatically by the LLM Guard library:
pip install llm-guard
from llm_guard.input_scanners import PromptInjection
scanner = PromptInjection()
result = scanner.scan("Your prompt here")
print(result)
The model will be downloaded automatically when the corresponding scanner is used.
About LLM Guard
LLM Guard is a comprehensive security toolkit for Large Language Models, providing:
- 🛡️ Prompt injection detection
- 🔒 PII detection and anonymization
- 🚫 Toxicity filtering
- ⚖️ Bias detection
- 📊 And many more security features
Repository: https://github.com/akto-api-security/llm-guard
License
MIT License
Maintained by Akto API Security
Model info
Created: 2025-11-30
Updated: 2025-11-30
View on Hugging Face