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