Update app.py

create workaround for different models

app.py

@@ -4,7 +4,7 @@ import requests
 import pytz
 import yaml
 from tools.final_answer import FinalAnswerTool
-
+from smolagents import VLLMModel
 from Gradio_UI import GradioUI
 
 # Below is an example of a tool that does nothing. Amaze us with your creativity !
@@ -39,12 +39,19 @@ 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 = 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,
+# )
+
+# Use VLLM based models: https://huggingface.co/docs/smolagents/en/reference/models#smolagents.VLLMModel
+
+
+model = VLLMModel(model_id="HuggingFaceTB/SmolLM-135M-Instruct")
+
+print(model([{"role": "user", "content": "Ok!"}], stop_sequences=["great"]))
 
 
 # Import tool from Hub