Update app.py

app.py

@@ -25,20 +25,19 @@ def respond(message, history):
     # Add current message
     prompt += f"User: {message}\nAssistant: "
     
-    # Generate response with streaming
-    response = ""
-    for token in pipe(
+    # Generate response
+    response = pipe(
         prompt,
         max_new_tokens=256,
         temperature=0.7,
         do_sample=True,
         pad_token_id=pipe.tokenizer.eos_token_id,
         return_full_text=False,
-        stream=True,
-    ):
-        chunk = token[0]["generated_text"]
-        response = chunk
-        yield response
+    )
+    
+    # Extract and yield the generated text
+    generated_text = response[0]["generated_text"]
+    yield generated_text
 
 # Create the chat interface
 demo = gr.ChatInterface(