Update app.py

app.py

@@ -51,7 +51,7 @@ def generate(
 additional_inputs = [
     gr.Textbox(label="System Prompt", max_lines=1, interactive=True),
     gr.Slider(label="Temperature", value=0.9, minimum=0.0, maximum=1.0, step=0.05, interactive=True, info="Higher values produce more diverse outputs"),
-    gr.Slider(label="Max new tokens", value=9048, minimum=256, maximum=9048, step=64, interactive=True, info="The maximum numbers of new tokens"),
+    gr.Slider(label="Max new tokens", value=4096, minimum=256, maximum=9048, step=64, interactive=True, info="The maximum numbers of new tokens"),
     gr.Slider(label="Top-p (nucleus sampling)", value=0.90, minimum=0.0, maximum=1, step=0.05, interactive=True, info="Higher values sample more low-probability tokens"),
     gr.Slider(label="Repetition penalty", value=1.2, minimum=1.0, maximum=2.0, step=0.05, interactive=True, info="Penalize repeated tokens")
 ]