Transformers How to use nanom/pix2struct-vizwizvqa-base with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("visual-question-answering", model="nanom/pix2struct-vizwizvqa-base") # Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText
processor = AutoProcessor.from_pretrained("nanom/pix2struct-vizwizvqa-base")
model = AutoModelForImageTextToText.from_pretrained("nanom/pix2struct-vizwizvqa-base") 
