How to use YuukiAsuna/VieTable-donut-docvqa-demo with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("document-question-answering", model="YuukiAsuna/VieTable-donut-docvqa-demo")
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("YuukiAsuna/VieTable-donut-docvqa-demo") model = AutoModelForMultimodalLM.from_pretrained("YuukiAsuna/VieTable-donut-docvqa-demo", device_map="auto")
https://huggingface.co/YuukiAsuna/VieTable-donut-docvqa-demo/resolve/main/tokenizer.json
hf download hf://YuukiAsuna/VieTable-donut-docvqa-demo/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/YuukiAsuna/VieTable-donut-docvqa-demo/resolve/main/tokenizer.json
