How to use hf-tiny-model-private/tiny-random-ViltForQuestionAnswering 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="hf-tiny-model-private/tiny-random-ViltForQuestionAnswering")
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForVisualQuestionAnswering processor = AutoProcessor.from_pretrained("hf-tiny-model-private/tiny-random-ViltForQuestionAnswering") model = AutoModelForVisualQuestionAnswering.from_pretrained("hf-tiny-model-private/tiny-random-ViltForQuestionAnswering", device_map="auto")
SFconvertbot