Update app.py

app.py

@@ -33,6 +33,8 @@ def respond(
         stream=True,
         temperature=temperature,
         top_p=top_p,
+        top_k=20,
+        repetition_penalty=1.1,
     ):
         token = message.choices[0].delta.content
 
@@ -47,12 +49,12 @@ demo = gr.ChatInterface(
     respond,
     additional_inputs=[
         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+        gr.Slider(minimum=1, maximum=2048, value=1024, 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,
             maximum=1.0,
-            value=0.95,
+            value=0.8,
             step=0.05,
             label="Top-p (nucleus sampling)",
         ),