Changed the model

app.py

@@ -4,6 +4,7 @@ import requests
 import pytz
 import yaml
 from tools.final_answer import FinalAnswerTool
+from smolagents import InferenceClientModel  # instead of HfApiModel
 
 from Gradio_UI import GradioUI
 
@@ -38,12 +39,22 @@ 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 = InferenceClientModel(model="google/flan-t5-xl")  # or try "flan-t5-base" if you want faster speed
 
-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 require credits
+#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,
+#)
+
+from smolagents import InferenceClientModel  # instead of HfApiModel
+
+model = InferenceClientModel(
+    model="google/flan-t5-xl",  # Free-tier, no credits required
+    max_tokens=512,
+    temperature=0.5,
 )