Update app.py

app.py

@@ -7,7 +7,7 @@ from transformers import (
     AutoModelForCausalLM
 )
 
-MODEL_NAME = "Qwen/Qwen2.5-0.5B-Instruct"
+MODEL_NAME = "microsoft/Phi-3.5-mini-instruct""
 
 print("Loading model...")
 
@@ -135,6 +135,7 @@ def generate_response(prompt):
     device = "cuda" if torch.cuda.is_available() else "cpu"
     
     model = model.to(device)
+
     
     inputs = {k: v.to(device) for k, v in inputs.items()}