Trial and error.

app.py

@@ -17,25 +17,12 @@ class BasicAgent:
     def __init__(self):
         print("BasicAgent initialized.")
 
-        print("Loading Qwen2.5-7B-Instruct model...")
-        self.model_name = "Qwen/Qwen2.5-1.5B-Instruct"
-        
-        # Load model and tokenizer
-        try:
-            self.tokenizer = AutoTokenizer.from_pretrained(self.model_name)
-            self.model = AutoModelForCausalLM.from_pretrained(
-                self.model_name,
-                torch_dtype="auto",
-                device_map="auto"
-            )
-            print(f"Successfully loaded {self.model_name}")
-        except Exception as e:
-            print(f"Error loading model: {e}")
-            # Fallback to HuggingFace Inference API if local loading fails
-            print("Falling back to InferenceClient")
-            self.client = InferenceClient(model=self.model_name)
-            self.tokenizer = None
-            self.model = None
+        print("Loading Mistral-Nemo-Instruct-2407 model...")
+        self.model_name = "mistralai/Mistral-Nemo-Instruct-2407"
+        self.client = InferenceClient(model=self.model_name)
+        self.tokenizer = None
+        self.model = None
+
 
     def __call__(self, question: str) -> str:
         print(f"Agent received question (first 50 chars): {question[:50]}...")
@@ -43,7 +30,7 @@ class BasicAgent:
         try:
             # Create messages for the model
             messages = [
-                {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."},
+                {"role": "system", "content": "You are Mistral, a helpful AI assistant. Answer the user's questions accurately and helpfully."},
                 {"role": "user", "content": question}
             ]
 
@@ -74,7 +61,7 @@ class BasicAgent:
                 answer = self.tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
             else:
                 # Fallback to Inference API
-                answer = self.client.chat(messages=messages)
+                answer = self.client.chat(messages)
                 
             print(f"Agent generated response (first 50 chars): {answer[:50]}...")
             return answer