Update app.py

app.py

@@ -39,7 +39,7 @@ def respond(
     )
     
     settings = provider.get_provider_default_settings()
-    settings.max_tokens = 2000
+    settings.max_tokens = max_tokens
     settings.stream = True
 
     messages = BasicChatHistory()
@@ -71,7 +71,7 @@ demo = gr.ChatInterface(
     respond,
     additional_inputs=[
         gr.Textbox(value="You are a helpful assistant.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+        gr.Slider(minimum=1, maximum=4096, value=4096, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(
             minimum=0.1,