Update app.py

app.py

@@ -1,3 +1,5 @@
+print("starting")
+
 import gradio as gr
 from huggingface_hub import hf_hub_download
 from llama_cpp import Llama
@@ -7,13 +9,15 @@ model_path = hf_hub_download(
     filename="llama-3-8b.Q4_K_M.gguf", 
 )
 
+print("downloading model")
 # Load the model (CPU optimized)
 llm = Llama(
     model_path=model_path,
     n_ctx=2048,
-    n_threads=2, 
+    n_threads=2,
+    verbose = True
 )
-
+print("loading model")
 def generate_test(user_code):
     prompt = f"""Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.