Update app.py

app.py

@@ -37,8 +37,6 @@ def load_quantized_model(model_id, model_basename):
 # Making the code device-agnostic
 model, tokenizer = load_quantized_model(model_name_or_path, "model.safetensors")
 
-
-
 def load_model_norm():
     if torch.cuda.is_available():
         print("CUDA is available. GPU will be used.")
@@ -59,6 +57,7 @@ def load_model_norm():
 
     
 # Function to generate a response using the model
+    
 def generate_response(prompt: str) -> str:
     PERSONA_NAME = "Ivana"
     PERSONA_DESC = f"""PROMPT_TEMPLATE_START
@@ -99,6 +98,7 @@ def generate_response(prompt: str) -> str:
 
 
 
+
 @app.get("/", tags=["Home"])
 async def api_home():
     return {'detail': 'Welcome to Eren Bot!'}