Update app.py

app.py

@@ -112,12 +112,14 @@ with gr.Blocks() as demo:
                     "max_new_tokens": max_new_tokens,
                     "temperature": temperature,
                 }
-                inference = pipe(sequences=message, streaming=True, **generation_config)
+                inference = pipe(sequences=message, streaming=False, **generation_config)
                 history[-1][1] += message
-                for token in inference:
-                    history[-1][1] += token.generations[0].text
-                    yield history
+                history[-1][1] += inference.generations[0].text
+                # for token in inference:
+                #     history[-1][1] += token.generations[0].text
+                #     yield history
                 print(pipe.timer_manager)
+                return history
 
             textbox.submit(
                 fn=clear_and_save_textbox,