How to use katanaml/donut-demo 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="katanaml/donut-demo")
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("katanaml/donut-demo") model = AutoModelForMultimodalLM.from_pretrained("katanaml/donut-demo", device_map="auto")
https://huggingface.co/katanaml/donut-demo/resolve/main/tokenizer.json
hf download hf://katanaml/donut-demo/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/katanaml/donut-demo/resolve/main/tokenizer.json
