ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision
Paper • 2102.03334 • Published
# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForVisualQuestionAnswering
processor = AutoProcessor.from_pretrained("hf-internal-testing/tiny-vilt-random-vqa")
model = AutoModelForVisualQuestionAnswering.from_pretrained("hf-internal-testing/tiny-vilt-random-vqa", device_map="auto")Quick Links
A tiny randomly-initialized ViLT used for unit tests in the Transformers VQA pipeline
- Downloads last month
- 17,878
# 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="hf-internal-testing/tiny-vilt-random-vqa")