Update app.py

app.py

@@ -25,20 +25,11 @@ hf_hub_download(
 if not os.path.exists(model_path):
     raise FileNotFoundError(f"Model file not found at {model_path}")
 
-print("Loading the model...")
 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):  
-    try:
-        conversation = ""
-        for msg in history:
-            role, content = msg
-            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)
+    try:   
+        response = llm(message, max_tokens=max_tokens, temperature=temperature, top_p=top_p)
         return response["choices"][0]["text"].strip()
         
     except Exception as e:
@@ -52,9 +43,3 @@ if __name__ == "__main__":
     )
 
     gguf_demo.launch(share=True)
-
-    try:
-        if llm:
-            llm.close()
-    except Exception as e:
-        print(f"Error closing model: {e}")