Update app.py

app.py

@@ -112,7 +112,7 @@ with gr.Blocks() as demo:
                     "max_new_tokens": max_new_tokens,
                     "temperature": temperature,
                 }
-                inference = pipe(sequences=message, streaming=False, **generation_config)
+                inference = pipe(sequences=message, streaming=True, **generation_config)
                 history[-1][1] += message
                 for token in inference:
                     history[-1][1] += token.generations[0].text