Update app.py

app.py

@@ -11,7 +11,7 @@ class XylariaChat:
 
         # Initialize the inference client
         self.client = InferenceClient(
-            model="Qwen/Qwen-32B-Preview",  # Changed model name
+            model="Qwen/QwQ-32B-Preview",  # Changed model name
             token=self.hf_token
         )
 
@@ -138,7 +138,7 @@ Capabilities:
 
             # Streaming output
             for response_text in response_stream:
-                full_response += response_text + "<|im_end|>" # Add <|im_end|> here
+                full_response += response_text
 
                 # Update the last message in chat history with partial response
                 updated_history[-1][1] = full_response