facebook

/

dinov3-vit7b16-pretrain-lvd1689m

like 111

Follow

AI at Meta 7.41k

While support for the DINOv3 models has been added on 2025-08-14 to the Transformers library, there isn't yet a released version of the Transformers library with this support. Trying to use DINOv3 models on Hugging Face Hub with existing released versions of the Transformers library will instead yield this kind of error:

ValueError: The checkpoint you are trying to load has model type `dinov3_vit`
but Transformers does not recognize this architecture. This could be because
of an issue with the checkpoint, or because your version of Transformers is out
of date.

You can update Transformers with the command `pip install --upgrade
transformers`. If this does not work, and the checkpoint is very new, then
there may not be a release version that supports this model yet. In this case,
you can get the most up-to-date code by installing Transformers from source
with the command `pip install git+https://github.com/huggingface/transformers.git`

Users who want to use the models will instead have to install the transformers package from source via pip install git+https://github.com/huggingface/transformers.git as advised in the above error message.