Update app.py

app.py

@@ -85,7 +85,7 @@ def generate_text(
             llm = Llama(
                 model_path=model_path,
                 flash_attn=True,
-                # n_gpu_layers=999,  # Let llama-cpp handle this automatically, or set a reasonable value.
+                n_gpu_layers=999,  # Let llama-cpp handle this automatically, or set a reasonable value.
                 n_ctx=n_ctx,      # Context window size.  Can increase.
                 verbose=False  #Reduce unnecessary verbosity
             )