Transformers How to use google/pix2struct-widget-captioning-base with Transformers:
# Use a pipeline as a high-level helper
# Warning: Pipeline type "visual-question-answering" is no longer supported in transformers v5.
# You must load the model directly (see below) or downgrade to v4.x with:
# pip install "transformers<5.0.0"
from transformers import pipeline
pipe = pipeline("visual-question-answering", model="google/pix2struct-widget-captioning-base") # pip install -U transformers accelerate
# 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", device_map="auto") 
