Update app.py

app.py

@@ -24,7 +24,7 @@ def generate(
 
     generate_kwargs = dict(
         temperature=temperature,
-        max_new_tokens=8000,
+        max_new_tokens=4000,
         top_p=top_p,
         repetition_penalty=repetition_penalty,
         do_sample=True,
@@ -52,15 +52,6 @@ additional_inputs=[
         interactive=True,
         info="Higher values produce more diverse outputs",
     ),
-    gr.Slider(
-        label="Max new tokens",
-        value=8000,
-        minimum=4000,
-        maximum=16000,
-        step=64,
-        interactive=True,
-        info="The maximum numbers of new tokens",
-    ),
     gr.Slider(
         label="Top-p (nucleus sampling)",
         value=0.90,