Update app.py

app.py

@@ -10,7 +10,7 @@ from huggingface_hub import hf_hub_download
 llm = Llama(
     model_path=hf_hub_download(
         repo_id=os.environ.get("REPO_ID", "TheBloke/Llama-2-7b-Chat-GGUF"),
-        filename=os.environ.get("MODEL_FILE", "llama-2-7b-chat.Q5_0.gguf"),
+        filename=os.environ.get("MODEL_FILE", "llama-2-7b-chat.Q4_K_M.gguf"),
     ),
     n_ctx=2048,
     n_gpu_layers=50, # change n_gpu_layers if you have more or less VRAM