Update app.py

app.py

@@ -32,7 +32,7 @@ def generate_response(message, history, system_prompt, temperature, top_p, top_k
     inputs = tokenizer(prompt, return_tensors="pt")
     streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=False)
     
-        generation_kwargs = dict(
+    generation_kwargs = dict(
         inputs,
         streamer=streamer,
         max_new_tokens=int(max_tokens),
@@ -40,9 +40,7 @@ def generate_response(message, history, system_prompt, temperature, top_p, top_k
         temperature=float(temperature) if temperature > 0.0 else 1.0,
         top_p=float(top_p),
         top_k=int(top_k)
-        
     )
-
     
     thread = Thread(target=model.generate, kwargs=generation_kwargs)
     thread.start()
@@ -59,7 +57,6 @@ with gr.Blocks() as demo:
     with gr.Row():
         # Left Workspace Column: Chat Layout
         with gr.Column(scale=3):
-            # FIXED: Removed type="messages" since it is default and unsupported as a kwarg in Gradio 6
             chatbot = gr.Chatbot(height=500)
             msg_input = gr.Textbox(placeholder="Enter reasoning prompt...", label="Your Message")
             with gr.Row():
@@ -95,7 +92,7 @@ with gr.Blocks() as demo:
             yield history
 
     # Event Wiring Flow
-    submit_event = msg_input.submit(
+    msg_input.submit(
         user_side_submit, [msg_input, chatbot], [msg_input, chatbot], queue=False
     ).then(
         bot_side_inference,