Update app.py

app.py

@@ -33,7 +33,7 @@ def format_prompt(message, history):
   return prompt
 
 def generate(
-    prompt, history, temperature=0.9, top_p=0.95,
+    prompt, history, temperature=0.9, top_p=0.95, max_new_tokens=256,repetition_penalty=1.0,
 ):
     
     temperature = float(temperature)
@@ -49,9 +49,10 @@ def generate(
     output = ""
     output=llm(formatted_prompt,
                temperature=temperature,
-        max_tokens=30,
+        max_tokens=max_new_tokens,
+               repeat_penalty=repetition_penalty,
         top_p=top_p,)
-    output=formatted_prompt+"ans:"+output
+    # output=formatted_prompt+"ans:"+output
     # for response in stream:
     #     output += response.token.text
     #     yield output
@@ -78,6 +79,24 @@ additional_inputs=[
         interactive=True,
         info="Higher values sample more low-probability tokens",
     ),
+    gr.Slider(
+        label="Max new tokens",
+        value=256,
+        minimum=0,
+        maximum=1048,
+        step=64,
+        interactive=True,
+        info="The maximum numbers of new tokens",
+    ),
+        gr.Slider(
+        label="Repetition penalty",
+        value=1.2,
+        minimum=1.0,
+        maximum=2.0,
+        step=0.05,
+        interactive=True,
+        info="Penalize repeated tokens",
+    )
 
 ]
 
@@ -99,4 +118,4 @@ with gr.Blocks(css=css) as demo:
         examples=[["What is the secret to life?"], ["Write me a recipe for pancakes."]]
     )
 
-demo.queue().launch(debug=True)
+demo.queue(max_size=20).launch(debug=True)