How to use naver-clova-ix/donut-base with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" 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("image-to-text", model="naver-clova-ix/donut-base")
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("naver-clova-ix/donut-base") model = AutoModelForMultimodalLM.from_pretrained("naver-clova-ix/donut-base", device_map="auto")
https://huggingface.co/naver-clova-ix/donut-base/resolve/main/tokenizer.json
hf download hf://naver-clova-ix/donut-base/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/naver-clova-ix/donut-base/resolve/main/tokenizer.json
