Update app.py

app.py

@@ -4,6 +4,8 @@ import requests
 import pytz
 import yaml
 from tools.final_answer import FinalAnswerTool
+from smolagents import LiteLLMModel
+
 
 from Gradio_UI import GradioUI
 
@@ -68,11 +70,10 @@ 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
-custom_role_conversions=None,
+model = LiteLLMModel(
+    model_id="qwen2:7b",  # Ollama strips "ollama_chat/"
+    api_base="http://127.0.0.1:11434",
+    num_ctx=8192,
 )