Update app.py

app.py

@@ -3,11 +3,13 @@ import base64
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import gradio as gr
 from PIL import Image
+from transformers import Owlv2Processor, Owlv2ForObjectDetection
 
-# Load the Hugging Face model and tokenizer
-model_id = "meta-llama/llama-3-2-90b-vision-instruct"
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id)
+model_id = "IDEA-Research/grounding-dino-base"
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+processor = AutoProcessor.from_pretrained(model_id)
+model = AutoModelForZeroShotObjectDetection.from_pretrained(model_id).to(device)
 
 def input_image_setup(uploaded_file):
     """