Update README.md

README.md

@@ -6,17 +6,17 @@ tags: [green, p1, llmware-encoder, ov]
 
 # unitary-toxic-roberta-ov  
 
-**unitary-toxic-roberta-ov** is a toxicity classifier from [unitary/unbiased-toxic-roberta](https://www.huggingface.com/unitary/unbiased-toxic-roberta), packaged in OpenVino format. 
+**unitary-toxic-roberta-ov** is a prompt injection risk classifier from [protectai/deberta-v3-base-prompt-injection-v2](https://www.huggingface.com/protectai/deberta-v3-base-prompt-injection-v2), packaged in OpenVino format. 
 
-The classifier can be used to evaluate toxic content in a prompt or in model output.  
+The classifier can be used to evaluate prompt injection risk in a prompt.  
 
 ### Model Description
 
-- **Developed by:** unitary
+- **Developed by:** protectai
 - **Quantized by:** llmware
-- **Model type:** roberta  
-- **Parameters:** 125 million
-- **Model Parent:** unitary/unbiased-toxic-roberta
+- **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