Update app.py

app.py

@@ -79,8 +79,6 @@ def respond(
                 n_gpu_layers=0,
                 n_batch=16,
                 n_ctx=2048,
-                n_threads=2,
-                use_mmap=True
             )
             llm_model = model
         provider = LlamaCppPythonProvider(llm)
@@ -160,7 +158,7 @@ demo = gr.ChatInterface(
         ),
         gr.Slider(
             minimum=512,
-            maximum=2048,
+            maximum=1024,
             value=1024,
             step=1,
             label="Max Tokens",