adding AutoModelForImageToText

app.py

@@ -1,7 +1,7 @@
 import streamlit as st
 from PIL import Image
 import torch
-from transformers import Qwen2VLForConditionalGeneration, AutoProcessor, pipeline
+from transformers import Qwen2VLForConditionalGeneration, AutoProcessor, AutoModelForImageToText
 from colpali_engine.models import ColPali, ColPaliProcessor
 import os
 
@@ -9,7 +9,8 @@ device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
 hf_token = os.getenv('HF_TOKEN')
 try:
-    model = pipeline("image-to-text", model="google/paligemma-3b-mix-448", use_auth_token=hf_token)
+    processor = AutoProcessor.from_pretrained("google/paligemma-3b-mix-448", use_auth_token=hf_token)
+    model = AutoModelForImageToText.from_pretrained("google/paligemma-3b-mix-448", use_auth_token=hf_token)
 except Exception as e:
     st.error(f"Error loading image-to-text model: {e}")
     st.stop()