Update app.py

app.py

@@ -9,7 +9,8 @@ from huggingface_hub import HfFolder
 HfFolder.save_token(HF_TOKEN)
 
 import transformers
-from transformers import pipeline, AutoTokenizer, AutoModel
+from transformers import VisionEncoderDecoderModel, AutoTokenizer, pipeline, AutoModel
+
 import streamlit as st
 
 # Set Hugging Face API Token if required
@@ -40,8 +41,10 @@ if uploaded_file is not None:
 
 # Load model directly for further analysis or different processing steps
 st.header("Load Model Directly")
+
+# Assuming 'nlpconnect/vit-gpt2-image-captioning' is your model identifier
+model = VisionEncoderDecoderModel.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
 tokenizer = AutoTokenizer.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
-model = AutoModel.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
 
 # Example of how you might use model and tokenizer directly
 # This section can be customized based on what you need to do with the model