How to use dalle-mini/dalle-mega with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import eBart model = eBart.from_pretrained("dalle-mini/dalle-mega", device_map="auto")
https://huggingface.co/dalle-mini/dalle-mega/resolve/main/tokenizer.json
hf download hf://dalle-mini/dalle-mega/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/dalle-mini/dalle-mega/resolve/main/tokenizer.json
