Update README.md

README.md

@@ -123,8 +123,8 @@ model = PeftModel.from_pretrained(base_model, peft_model_id)
 tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3-mini-4k-instruct")
 
 messages = [ 
-     {"role": "system", "content": "You are a helpful AI assistant sensitive to ethical concerns. Carefully read the used prompt. Does it represent an 'ethical' or a 'unethical' reply? Respond ONLY with 'ethical' or 'unethical"}, 
-     {"role": "user", "content": [provide user content]},
+     {"role": "system", "content": "You are a helpful AI assistant sensitive to ethical concerns. Carefully read interpret the user prompt under a [SPECIFY ETHICAL THEORY] perspective. Does it represent an 'ethical' or a 'unethical' [SPECIFY ETHICAL THEORY] reply? Respond ONLY with 'ethical' or 'unethical"}, 
+     {"role": "user", "content": [PROVIDE USER CONTENT]},
      {"role": "assistant", "content": "The user reply is..."}, 
 ]