Update app.py

app.py

@@ -9,7 +9,7 @@ import gradio as gr
 # 1. Load model via llama-cpp-python
 model = Llama.from_pretrained(
     repo_id="openbmb/MiniCPM-V-2_6-gguf",
-    filename="*.gguf",
+    filename="ggml-model-Q4_K_M.gguf", # Choose a specific GGUF file
     n_ctx=4096,
 )
 # 2. Setup RAG