Instructions to use docling-project/docling-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use docling-project/docling-models with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("docling-project/docling-models", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Docling can be run on GPU?
#15
by streebo - opened
I have a mac studio machine , pleaes guide how can i use MPS to fasten the docling process currently it is taking 15 seconds per page in PDF on highend CPU machine.
We are working on MPS accelerated versions of the layout and table-model. Please submit all your requests in the issue-tracker for docling (https://github.com/docling-project/docling/issues).
PeterWJStaar changed discussion status to closed