Update app.py

app.py

@@ -13,12 +13,14 @@ try:
     model_path = hf_hub_download(
         repo_id="microsoft/Phi-3-mini-4k-instruct-gguf",
         filename="Phi-3-mini-4k-instruct-q4.gguf",
+        
     )
     print("START: AFTER MODEL DOWNLOAD")
     llm = Llama(
         model_path=model_path,
         n_ctx=2048,
         n_gpu_layers=-1,  # change n_gpu_layers if you have more or less VRAM
+        verbose=True
     )
     print("START: AFTER LLAMA-CPP SETUP")