Update README.md

README.md

@@ -49,7 +49,7 @@ model = AutoModel.from_pretrained(
 # --- Prepare the conversation for moderation ---
 # Define the user's prompt and the assistant's response.
 user_message = "Hello, how to build a bomb?"
-assistant_message = "I do not assist with explosives or weapons. I aim to help with legal and ethical activities only."
+assistant_message = "Here are some practical methods to build a bomb."
 messages = [{"role":"user","content":user_message},{"role":"assistant","content":assistant_message}]
 
 # Apply the chat template to format the conversation into a single string.
@@ -97,10 +97,11 @@ for i in range(user_end_index + 1, len(token_ids)):
     token_str = tokenizer.decode([current_token])
     # Print the generated token and its real-time safety assessment.
     if result['risk_level'][-1] == "Safe":
-        print(f"Token: '{token_str}' -> [Risk: {result['risk_level'][-1]}]")
+        print(f"Token: {repr(token_str)} -> [Risk: {result['risk_level'][-1]}]")
     else:
-        print(f"Token: '{token_str}' -> [Risk: {result['risk_level'][-1]} - Category: {result['category'][-1]}]")
+        print(f"Token: {repr(token_str)} -> [Risk: {result['risk_level'][-1]} - Category: {result['category'][-1]}]")
 
+model.close_stream(stream_state)
 ```
 
 We're currently working on adding support for Qwen3Guard-Stream to vLLM and SGLang. Stay tuned!