Update app.py

app.py

@@ -323,8 +323,7 @@ examples = [
 DESCRIPTION = """\
 <img src='https://huggingface.co/spaces/huggingface-projects/gemma-3-12b-it/resolve/main/assets/logo.png' id='logo' />
 
-This is a demo of Gemma 3 12B it, a vision language model with outstanding performance on a wide range of tasks.
-You can upload images, interleaved images and videos. Note that video input only supports single-turn conversation and mp4 input.
+Demo Gemma 3 12B it untuk Constraining
 """
 
 demo = gr.ChatInterface(
@@ -334,7 +333,7 @@ demo = gr.ChatInterface(
     textbox=gr.MultimodalTextbox(file_types=["image", ".mp4"], file_count="multiple", autofocus=True),
     multimodal=True,
     additional_inputs=[
-        gr.Textbox(label="System Prompt", value="You are a helpful assistant."),
+        gr.Textbox(label="Constraining Prompt", value="Kamu adalah ahli Bahasa Sunda."),
         gr.Slider(label="Max New Tokens", minimum=100, maximum=2000, step=10, value=700),
     ],
     stop_btn=False,