Update app.py

app.py

@@ -30,9 +30,6 @@ llm = Llama(model_path=model_path)
 print("Model loaded successfully!")
 
 def generate_response(message, history, temperature=0.7, top_p=1.0, max_tokens=256):  
-     """
-    Generate a response based on the user's message and the conversation history.
-    """
     try:
         conversation = ""
         for msg in history:
@@ -40,10 +37,10 @@ def generate_response(message, history, temperature=0.7, top_p=1.0, max_tokens=2
             conversation += f"<start_of_turn>{role}\n{content}\n<end_of_turn>"
 
         conversation += f"<start_of_turn>user\n{message}\n<end_of_turn>"
-
+    
         response = llm(conversation, max_tokens=max_tokens, temperature=temperature, top_p=top_p)
         return response["choices"][0]["text"].strip()
-
+        
     except Exception as e:
         return f"Error generating response: {str(e)}"