Update app.py

app.py

@@ -14,7 +14,7 @@ processor = AutoProcessor.from_pretrained(ckpt)
 
 
 @spaces.GPU()
-def bot_streaming(message, history, max_new_tokens=250):
+def bot_streaming(message, history, max_new_tokens=2048):
     
     txt = message["text"]
     ext_buffer = f"{txt}"
@@ -86,13 +86,13 @@ demo = gr.ChatInterface(fn=bot_streaming, title="Multimodal Llama", examples=[
       additional_inputs = [gr.Slider(
               minimum=10,
               maximum=500,
-              value=250,
+              value=2048,
               step=10,
               label="Maximum number of new tokens to generate",
           )
         ],
       cache_examples=False,
-      description="Try Multimodal Llama by Meta with transformers in this demo. Upload an image, and start chatting about it, or simply try one of the examples below. To learn more about Llama Vision, visit [our blog post](https://huggingface.co/blog/llama32). ",
+      description="Try Multimodal with transformers in this demo. Upload an image, and start chatting about it, or simply try one of the examples below. ",
       stop_btn="Stop Generation", 
       fill_height=True,
     multimodal=True)