Instructions to use microsoft/dit-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/dit-large with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, BeitForMaskedImageModeling processor = AutoImageProcessor.from_pretrained("microsoft/dit-large") model = BeitForMaskedImageModeling.from_pretrained("microsoft/dit-large", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add MIT license metadata
#4
by muhammadsaeed1 HF Staff - opened
License confirmed by Tengchao Lv (Microsoft Research, DiT co-author) by email on 2026-10-09: the MIT license of microsoft/unilm also applies to the released DiT weights.
julien-c changed pull request status to merged