Update app.py

app.py

@@ -23,6 +23,7 @@ try:
         filename="ggml-model-Q4_K_M.gguf",
         n_ctx=4096,
         n_threads=os.cpu_count(),
+        n_batch=512,
         verbose=False, # Set to True for more debug output
         # `chat_format` can sometimes be inferred from model, but explicitly setting for safety:
         # MiniCPM-V-2_6-gguf uses a specific chat template.