Transformers How to use deepmind/vision-perceiver-conv with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("image-classification", model="deepmind/vision-perceiver-conv")
pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png") # pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForImageClassification
tokenizer = AutoTokenizer.from_pretrained("deepmind/vision-perceiver-conv")
model = AutoModelForImageClassification.from_pretrained("deepmind/vision-perceiver-conv", device_map="auto") 
