Update README.md

README.md

@@ -55,7 +55,7 @@ from llama_cpp import Llama
 
 model_path = hf_hub_download(
     repo_id="MoxoffSpA/VolareQuantized",
-    filename="Volare-Q4_K_M.gguf"
+    filename="Volare-ggml-Q4_K_M.gguf"
 )
 
 # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.