model meta-llama/Llama-3.2-3B-Instruct-QLORA_INT4_EO8

app.py

@@ -39,7 +39,8 @@ final_answer = FinalAnswerTool()
 model = HfApiModel(
     max_tokens=2096,
     temperature=0.5,
-    model_id='meta-llama/Llama-3.1-8B-Instruct',# it is possible that this model may be overloaded
+    #model_id='meta-llama/Llama-3.1-8B-Instruct',# it is possible that this model may be overloaded
+    model_id='meta-llama/Llama-3.2-3B-Instruct-QLORA_INT4_EO8',
     custom_role_conversions=None,
 )
 #model = OpenAIServerModel(