Update multimodal_queries.py

multimodal_queries.py

@@ -1,12 +1,13 @@
-import requests
+import re
 import base64
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import gradio as gr
+from PIL import Image
+import io
+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)
+processor = Owlv2Processor.from_pretrained("google/owlv2-large-patch14-finetuned")
+model = Owlv2ForObjectDetection.from_pretrained("google/owlv2-large-patch14-finetuned")
 
 def input_image_setup(uploaded_file):
     """