Update app.py

app.py

@@ -43,7 +43,7 @@ def chat(message, history, temperature, max_new_tokens):
     
     # Ensure the model is loaded before proceeding
     if not check_model_status():
-        yield "Model is not ready. Please try again later."
+        yield "Model is not ready. Please try again later.", ""
         return
     
     prompt = f"Human: {message}\n\nAssistant:"
@@ -126,10 +126,9 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
         bot_message = ""
         for partial_response, token_status_value in chat(message, chat_history, temperature, max_new_tokens):
             bot_message = partial_response
-            token_status.update(value=token_status_value)  # Update token generation status
-            yield "", chat_history + [(message, bot_message)]
+            yield "", chat_history + [(message, bot_message)], gr.update(value=token_status_value)
     
-    send_button.click(respond, inputs=[textbox, chatbot, temperature_slider, max_tokens_slider], outputs=[textbox, chatbot])
+    send_button.click(respond, inputs=[textbox, chatbot, temperature_slider, max_tokens_slider], outputs=[textbox, chatbot, token_status])
     clear_button.click(lambda: [], None, chatbot)
     reload_button.click(reload_model_button, None, status_text)