Update app.py

app.py

@@ -6,11 +6,11 @@ import gradio as gr
 from gradio import FileData
 import time
 import spaces
+# Load model directly
+from transformers import AutoProcessor, AutoModelForPreTraining
 
-ckpt = "meta-llama/Llama-3.2-11B-Vision-Instruct"
-# Load model to CPU by default
-model = MllamaForConditionalGeneration.from_pretrained(ckpt, torch_dtype=torch.bfloat16)
-processor = AutoProcessor.from_pretrained(ckpt)
+processor = AutoProcessor.from_pretrained("meta-llama/Llama-3.2-11B-Vision-Instruct")
+model = AutoModelForPreTraining.from_pretrained("meta-llama/Llama-3.2-11B-Vision-Instruct")
 
 @spaces.CPU
 def bot_streaming(message, history, max_new_tokens=250):