Update app.py

app.py

@@ -11,7 +11,7 @@ client = InferenceClient(model="https://api-inference.huggingface.co/models/meta
 # query client using streaming mode
 def inference(message, history):
     partial_message = ""
-    for token in client.text_generation(message, max_new_tokens=50, stream=True):
+    for token in client.text_generation(message, max_new_tokens=100, stream=True):
         partial_message += token
         yield partial_message