Update app.py

app.py

@@ -19,12 +19,12 @@ For more information on `huggingface_hub` Inference API support, please check th
 """
 #client = InferenceClient(model="google/recurrentgemma-2b-it")
 #client = pipeline("text-generation", model="google/recurrentgemma-2b-it")
-
+max_tokens = 780
 def respond(
     message,
     history: list[tuple[str, str]],
     system_message,
-    max_tokens:"720",
+    max_tokens,
     temperature,
     top_p,
 ):