Update app.py

app.py

@@ -4,9 +4,13 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 
 # Load model and tokenizer
 model_name = "meta-llama/Llama-2-7b-chat-hf"
+print("started loading model")
 model = AutoModelForCausalLM.from_pretrained(model_name)
+print("loaded model")
 tokenizer = AutoTokenizer.from_pretrained(model_name)
+print("loaded tokenizer")
 chat_pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer)
+print("built pipeline")
 
 # Define the generate_response function
 def generate_response(prompt):