vijil
/

vijil_dome_prompt_injection_detection

prompt-injection

Model card Files Files and versions

vijilpd commited on 8 days ago

Commit

fa96f27

·

verified ·

1 Parent(s): 8e61299

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -22,7 +22,7 @@ This model is a fine-tuned version of ModernBert to classify prompt-injection pr
 ## Uses
 Prompt injection attacks manipulate language models by inserting or altering prompts to trigger harmful or unintended responses.
-The vijil/mbert-prompt-injection model is designed to enhance security in language model applications by detecting prompt-injection attacks.
 ## How to Get Started with the Model
@@ -31,7 +31,7 @@ from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipe
 import torch
 tokenizer = AutoTokenizer.from_pretrained("answerdotai/ModernBERT-base")
-model = AutoModelForSequenceClassification.from_pretrained("vijil/mbert-prompt-injection")
 classifier = pipeline(
   "text-classification",

 ## Uses
 Prompt injection attacks manipulate language models by inserting or altering prompts to trigger harmful or unintended responses.
+The vijil/vijil_dome_prompt_injection_detection model is designed to enhance security in language model applications by detecting prompt-injection attacks.
 ## How to Get Started with the Model
 import torch
 tokenizer = AutoTokenizer.from_pretrained("answerdotai/ModernBERT-base")
+model = AutoModelForSequenceClassification.from_pretrained("vijil/vijil_dome_prompt_injection_detection")
 classifier = pipeline(
   "text-classification",