Transformers How to use jmonas/ViLT-5M-vqa 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="jmonas/ViLT-5M-vqa") # pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForVisualQuestionAnswering
processor = AutoProcessor.from_pretrained("jmonas/ViLT-5M-vqa")
model = AutoModelForVisualQuestionAnswering.from_pretrained("jmonas/ViLT-5M-vqa", device_map="auto") 
