Update app.py

app.py

@@ -6,21 +6,19 @@ try:
         repo_id="operablepattern/gemma-2b-it-Q",
         filename="*Q5_K_M.gguf",
         chat_format="gemma",
-        max_tokens=32,
         verbose=True
     )
 except:
     llm = Llama(
         model_path="./gemma-2b-it-Q5_K_M.gguf",
         chat_format="gemma",
-        max_tokens=32,
         verbose=True
     )
 
 def response(message, history):
     print(message)
     print(history)
-    output = llm(message)
+    output = llm(message,max_tokens=32)
     print(output)
     return message