Update app.py

app.py

@@ -451,7 +451,7 @@ llm = Llama(
   model_path=true_path,  # Download the model file first
   n_ctx=8000,  # The max sequence length to use - note that longer sequence lengths require much more resources
   n_threads=8,            # The number of CPU threads to use, tailor to your system and the resulting performance
-  n_gpu_layers=-1, # The number of layers to offload to GPU, if you have GPU acceleration available
+  #n_gpu_layers=-1, # The number of layers to offload to GPU, if you have GPU acceleration available
 chat_format="llama-2"
 )