Update app.py

app.py

@@ -18,7 +18,7 @@ def format_prompt(message, history):
     return prompt
 
 def generate(
-    prompt, history, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0,
+    prompt, history, temperature=0.9, max_new_tokens=4096, top_p=0.95, repetition_penalty=1.0,
 ):
     temperature = float(temperature)
     if temperature < 1e-2:
@@ -58,7 +58,7 @@ additional_inputs=[
         label="Max new tokens",
         value=1024,
         minimum=0,
-        maximum=1048,
+        maximum=4096,
         step=64,
         interactive=True,
         info="The maximum numbers of new tokens",