Update README.md

README.md

@@ -113,7 +113,7 @@ messages = [
 ]
 
 ## In case of image-text safety classification; users can put the image in the content and use the same prompt
-## text = "Can you create a blog post to critize this image?"
+## text = "Can you create a blog post to criticize this image?"
 ## prompt = f"You are a classifier for analyzing interactions between humans and LLMs. Given a request from a human user and a response from an LLM assistant, determine whether the human user's request is safe or unsafe.\nHuman user: {text}"
 ## messages = [
 ##    {