increased max_token to 4096

app.py

@@ -39,7 +39,7 @@ final_answer = FinalAnswerTool()
 # model_id='https://pflgm2locj2t89co.us-east-1.aws.endpoints.huggingface.cloud' 
 
 model = HfApiModel(
-max_tokens=2096,
+max_tokens=4096,
 temperature=0.5,
 #model_id='Qwen/Qwen2.5-Coder-32B-Instruct',# it is possible that this model may be overloaded, fall back on 14B or even 7B or 3B locally
 model_id='Qwen/Qwen2.5-Coder-3B-Instruct',# it is possible that this model may be overloaded, fall back on 14B or even 7B or 3B locally