Update app.py

app.py

@@ -7,7 +7,7 @@ import gradio as gr
 from gradio import FileData
 import time
 import spaces
-ckpt = "meta-llama/Llama-3.2-11B-Vision-Instruct"
+ckpt = "mlx-community/Llama-3.2-11B-Vision-Instruct-abliterated"
 model = MllamaForConditionalGeneration.from_pretrained(ckpt,
     torch_dtype=torch.bfloat16).to("cuda")
 processor = AutoProcessor.from_pretrained(ckpt)
@@ -92,7 +92,7 @@ demo = gr.ChatInterface(fn=bot_streaming, title="Multimodal Llama", examples=[
           )
         ],
       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 Llama (Abliterated) by Mlx 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). ",
       stop_btn="Stop Generation", 
       fill_height=True,
     multimodal=True)