Update app.py

app.py

@@ -9,11 +9,14 @@ from huggingface_hub import hf_hub_download
 print("START: AFTER IMPORTS")
 
 try:
+    print("START: BEFORE MODEL DOWNLOAD")
+    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=hf_hub_download(
-            repo_id="microsoft/Phi-3-mini-4k-instruct-gguf",
-            filename="Phi-3-mini-4k-instruct-q4.gguf",
-        ),
+        model_path=model_path,
         n_ctx=2048,
         n_gpu_layers=-1,  # change n_gpu_layers if you have more or less VRAM
     )