Text Classification
Transformers
Safetensors
deberta-v2
prompt-injection
injection
security
llm-security
Generated from Trainer
text-embeddings-inference
# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("proventra/mdeberta-v3-base-prompt-injection")
model = AutoModelForSequenceClassification.from_pretrained("proventra/mdeberta-v3-base-prompt-injection", device_map="auto")Quick Links
mdeberta-v3-base-prompt-injection
This model is a fine-tuned version of microsoft/mdeberta-v3-base on a combination of jackhhao/jailbreak-classification, deepset/prompt-injections, a custom datasets containing known attacks, and injections nested in legitimate content like websites and articles.
Usage
from transformers import pipeline
classifier = pipeline(
"text-classification",
model="proventra/mdeberta-v3-base-prompt-injection"
)
print(classifier("Your text to scan"))
Use in Proventra Core
proventra-core python library
check out Proventra
- Downloads last month
- 3,841
Model tree for proventra/mdeberta-v3-base-prompt-injection
Base model
microsoft/mdeberta-v3-base
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="proventra/mdeberta-v3-base-prompt-injection")