Update app.py

app.py

@@ -21,6 +21,7 @@ def respond(
     max_tokens=512,
     temperature=0.5,
     top_p=1.0,
+    repetition_penalty=1.1,
 ):
     messages = [{"role": "system", "content": system_message}]
 
@@ -44,6 +45,7 @@ def respond(
         max_new_tokens = max_tokens,
         temperature = temperature,
         top_p = top_p,
+        repetition_penalty=repetition_penalty,
     )
     generated_ids = [
         output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
@@ -59,8 +61,8 @@ demo = gr.ChatInterface(
     respond,
     additional_inputs=[
         gr.Textbox(value="You are a helpful AI assistant and your name is RexLM.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, 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=1, maximum=4096, value=1024, step=1, label="Max new tokens"),
+        gr.Slider(minimum=0.1, maximum=4.0, value=0.5, step=0.1, label="Temperature"),
         gr.Slider(
             minimum=0.1,
             maximum=1.0,
@@ -68,6 +70,7 @@ demo = gr.ChatInterface(
             step=0.05,
             label="Top-p (nucleus sampling)",
         ),
+        gr.Slider(minimum=0.5, maximum=1.5, value=1.1, step=0.1, label="Repetation Penalty"),
     ],
 )