Update app.py

app.py

@@ -41,13 +41,20 @@ final_answer = FinalAnswerTool()
 # If the agent does not answer, the model is overloaded, please use another model or the following Hugging Face Endpoint that also contains qwen2.5 coder:
 # model_id='https://pflgm2locj2t89co.us-east-1.aws.endpoints.huggingface.cloud' 
 
-model = HfApiModel(
-max_tokens=2096,
-temperature=0.5,
-# model_id='Qwen/Qwen2.5-Coder-32B-Instruct',# it is possible that this model may be overloaded
-# model_id='https://pflgm2locj2t89co.us-east-1.aws.endpoints.huggingface.cloud',
-model_id='mistralai/Mistral-7B-Instruct-v0.2',
-custom_role_conversions=None,
+# model = HfApiModel(
+# max_tokens=2096,
+# temperature=0.5,
+# # model_id='Qwen/Qwen2.5-Coder-32B-Instruct',# it is possible that this model may be overloaded
+# # model_id='https://pflgm2locj2t89co.us-east-1.aws.endpoints.huggingface.cloud',
+# model_id='mistralai/Mistral-7B-Instruct-v0.2',
+# custom_role_conversions=None,
+# )
+
+from smolagents import LiteLLMModel
+model = LiteLLMModel(
+    model_id="ollama_chat/qwen2:7b", 
+    api_base="http://127.0.0.1:11434", 
+    num_ctx=8192
 )