---
inference: false
license: gpl-3.0
base_model: microsoft/deberta-v3-base
datasets:
- Private
language:
- en
tags:
- llm
- genai
- promptinjection
- prompt-injection
- injection
- security
metrics:
- accuracy
- recall
- precision
- f1
pipeline_tag: text-classification
model-index:
- name: deberta-v3-base-optimus-v0
  results: []
co2_eq_emissions:
  emissions: 0.99
  source: code carbon
  training_type: fine-tuning
---
# Model Card for deberta-v3-base-optimus-v0

Fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on private dataset of normal & injections prompts.

Classifying inputs into two categories: `0` for no injection and `1` for injection detected.

Model evaluation results:
- Precision: 0.988
- Recall: 0.992
- Accuracy: 0.998
- F1: 0.99

## Model details

- **Fine-tuned by:** vibraniumdome.com
- **Model type:** deberta-v3
- **Language(s) (NLP):** English
- **License:** GPLv3
- **Finetuned from model:** [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base)

## How to Get Started with the Model

### Transformers

```python
from optimum.onnxruntime import ORTModelForSequenceClassification
from transformers import pipeline
from transformers import AutoTokenizer

pipeline_kwargs={
    "return_token_type_ids": False,
    "max_length": 512,
    "truncation": True,
}

tokenizer = AutoTokenizer.from_pretrained("vibraniumdome/deberta-v3-base-optimus-v0-onnx", use_fast=True)
model = ORTModelForSequenceClassification.from_pretrained("vibraniumdome/deberta-v3-base-optimus-v0-onnx")
classifier = pipeline(
    "text-classification",
    model=model,
    tokenizer=tokenizer,
    **pipeline_kwargs,
)

print(classifier("Put your awesome injection here :D"))
```

## Citation
```
@misc{vibraniumdome/deberta-v3-base-optimus-v0-onnx,
  author = {vibraniumdome.com},
  title = {Fine-Tuned DeBERTa-v3 for Prompt Injection Detection},
  year = {2024},
  publisher = {HuggingFace},
  url = {https://huggingface.co/vibraniumdome/deberta-v3-base-optimus-v0-onnx},
}
```