How to use dandelin/vilt-b32-finetuned-coco with Transformers:
# Load model directly from transformers import AutoProcessor, ViltForImageAndTextRetrieval processor = AutoProcessor.from_pretrained("dandelin/vilt-b32-finetuned-coco") model = ViltForImageAndTextRetrieval.from_pretrained("dandelin/vilt-b32-finetuned-coco", device_map="auto")
nghiaday 
SFconvertbot