Update app.py

app.py

@@ -866,7 +866,7 @@ from llama_cpp import Llama
 llama = Llama(model_file_path,
                   n_ctx = 4090,
                   n_threads=2,            # The number of CPU threads to use, tailor to your system and the resulting performance
-                  n_gpu_layers=-1
+                  #n_gpu_layers=-1
                   )
 print("load {}".format(model_file_path))