Update app.py

Trying to reduce the tokens for the hgapimodel - based on input from discord

app.py

@@ -40,10 +40,11 @@ final_answer = FinalAnswerTool()
 # model_id='https://pflgm2locj2t89co.us-east-1.aws.endpoints.huggingface.cloud' 
 
 model = HfApiModel(
-max_tokens=2096,
+#max_tokens=2096,
+max_tokens=256,
 temperature=0.5,
 #model_id='Qwen/Qwen2.5-Coder-32B-Instruct',# it is possible that this model may be overloaded
-    model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct',# it is possible that this model may be overloaded
+model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct',# it is possible that this model may be overloaded
 custom_role_conversions=None,
 )