Update app.py

app.py

@@ -28,7 +28,6 @@ model_math_tool = ModelMathTool()
 # 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(model_id='mistralai/Mistral-7B-Instruct-v0.2', max_tokens=512)
 
 
 
@@ -53,11 +52,32 @@ def cache_answer(question: str, answer: str):
 
 
 
+# --- Model Setup ---
+MODEL_NAME = 'mistralai/Mistral-7B-Instruct-v0.2'
+
+def load_model():
+    """Download and load the model and tokenizer."""
+    try:
+        print(f"Loading model {MODEL_NAME}...")
+        model = AutoModelForCausalLM.from_pretrained(MODEL_NAME)
+        tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+        print(f"Model {MODEL_NAME} loaded successfully.")
+        return model, tokenizer
+    except Exception as e:
+        print(f"Error loading model: {e}")
+        raise
+
+# Load the model and tokenizer locally
+model, tokenizer = load_model()
+
+
+
 class BasicAgent:
     def __init__(self):
         print("BasicAgent initialized.")
         self.agent = CodeAgent(
             model=model,
+            tokenizer=tokenizer,
             tools=[web_search,python_interpreter,visit_webpage_tool,model_math_tool], 
             max_steps=1,
             verbosity_level=1,