Hugging Face's logo

llmware
/
protectai-prompt-injection-onnx

ONNX
deberta-v2
green
p1
llmware-encoder
Model card Files Community

protectai-prompt-injection-onnx

protectai-prompt-injection-onnx is a prompt injection risk classifier from protectai/deberta-v3-base-prompt-injection-v2, packaged in ONNX format.

The classifier can be used to evaluate prompt injection risk in a prompt.

Model Description

  • Developed by: protectai
  • Quantized by: llmware
  • Model type: deberta
  • Parameters: 184 million
  • Model Parent: protectai/deberta-v3-base-prompt-injection-v2
  • Language(s) (NLP): English
  • License: Apache 2.0
  • Uses: Prompt safety
  • RAG Benchmark Accuracy Score: NA
  • Quantization: int4

Model Card Contact

llmware on github

llmware on hf

llmware website

Downloads last month
31
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model authors have turned it off explicitly.

Model tree for llmware/protectai-prompt-injection-onnx

Base model

microsoft/deberta-v3-base
Finetuned
protectai/deberta-v3-base-prompt-injection-v2
Quantized
(3)
this model

Collection including llmware/protectai-prompt-injection-onnx