adding repetition penalty

app.py

@@ -18,6 +18,7 @@ def respond(
     max_tokens,
     temperature,
     top_p,
+    repetition_penalty,
 ):
     messages = [{"role": "system", "content": system_message}]
 
@@ -37,6 +38,7 @@ def respond(
         stream=True,
         temperature=temperature,
         top_p=top_p,
+        repetition_penalty=repetition_penalty,
         messages=messages,
     ):
         token = message.choices[0].delta.content
@@ -60,6 +62,14 @@ demo = gr.ChatInterface(
             label="Top-P",
             visible=True,
         ),
+        gr.Slider(
+            minimum=1.0,
+            maximum=2.0,
+            value=1.2,
+            step=0.05,
+            label="Repetition penalty",
+            visible=True,
+        ),
         
     ],
     fill_height=True,