Update app.py

app.py

@@ -15,7 +15,7 @@ try:
     print("Loading MiniCPM-V-2_6-gguf model...")
     llm = Llama.from_pretrained(
         repo_id="openbmb/MiniCPM-V-2_6-gguf",
-        filename="ggml-model-Q3_K_M.gguf",
+        filename="ggml-model-Q4_K_M.gguf",
         n_ctx=4096,
         n_threads=os.cpu_count(),
         n_batch=512, # Increased batch size for prompt processing