deepset
/

deberta-v3-base-injection

Text Classification

Generated from Trainer

text-embeddings-inference

Model card Files Files and versions

JasperLS commited on Jun 26, 2023

Commit

1a8d6fc

·

1 Parent(s): 45af46d

Some more details

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -21,7 +21,7 @@ It achieves the following results on the evaluation set:
 ## Model description
-This model detects prompt injections attempts.
 ## Intended uses & limitations
@@ -29,7 +29,7 @@ More information needed
 ## Training and evaluation data
-More information needed
 ## Training procedure

 ## Model description
+This model detects prompt injection attempts and classifies them as "INJECTION". Legitimate requests are classified as "LEGIT". The dataset assumes that legitimate requests are either all sorts of questions of key word searches.
 ## Intended uses & limitations
 ## Training and evaluation data
+Based in the [promp-injection](https://huggingface.co/datasets/JasperLS/prompt-injections) dataset.
 ## Training procedure