Update app.py

app.py

@@ -12,7 +12,7 @@ try:
     llm = Llama(
         model_path=hf_hub_download(
             repo_id="microsoft/Phi-3-mini-4k-instruct-gguf",
-            filename="*q4.gguf",
+            filename="Phi-3-mini-4k-instruct-q4.gguf",
         ),
         n_ctx=2048,
         n_gpu_layers=-1,  # change n_gpu_layers if you have more or less VRAM