Visual Question Answering
Transformers
PyTorch
English
vision-encoder-decoder
image-text-to-text
ui refexp
Instructions to use ivelin/donut-refexp-combined-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ivelin/donut-refexp-combined-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("visual-question-answering", model="ivelin/donut-refexp-combined-v1")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("ivelin/donut-refexp-combined-v1") model = AutoModelForMultimodalLM.from_pretrained("ivelin/donut-refexp-combined-v1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 4a445c9b5c20909e87718148210a74b495dc47df192825897ddd8c52ec64f75f
- Size of remote file:
- 809 MB
- SHA256:
- 265e6bf01027c22650e3f9d69a654aae72bbf977b5dd16bff7504a723de85266
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.