Update app.py

app.py

@@ -7,10 +7,11 @@ from gradio import FileData
 import time
 import spaces
 # Load model directly
+# Load model directly
 from transformers import AutoProcessor, AutoModelForPreTraining
 
-processor = AutoProcessor.from_pretrained("meta-llama/Llama-3.2-11B-Vision-Instruct")
-model = AutoModelForPreTraining.from_pretrained("meta-llama/Llama-3.2-11B-Vision-Instruct")
+processor = AutoProcessor.from_pretrained("unsloth/Llama-3.2-11B-Vision-Instruct-bnb-4bit")
+model = AutoModelForPreTraining.from_pretrained("unsloth/Llama-3.2-11B-Vision-Instruct-bnb-4bit")
 
 @spaces.CPU
 def bot_streaming(message, history, max_new_tokens=250):