This repository contains open-source models redistributed for easy integration with AddaxAI, hosted by Addax Data Science. Each model retains its original license (see license files) and attribution. We comply with all original license terms. Users must review and comply with individual model licenses before use. See below for detailed model information including original sources, licenses, and attributions.
Model name
DINOv2 ViT-S/14
Owner
Meta Platforms, Inc.
Developer
Meta AI (FAIR)
Links
Vendored DINOv2 source
This repo bundles a slimmed copy of the DINOv2 architecture source alongside the model weights, so AddaxAI can load the architecture from this Hugging Face repo instead of fetching it from github.com/facebookresearch/dinov2 at runtime.
This is needed because many AddaxAI users sit behind networks that allow huggingface.co but block or throttle GitHub, and the first run of the embedding step would otherwise fail with no internet access to github.com.
What is included
Only the files needed to load the vits14, vitb14, and vitl14 backbones for inference:
hubconf.py(slimmed to the three backbone entry points)LICENSE(Apache 2.0)dinov2/__init__.pydinov2/hub/__init__.py,dinov2/hub/backbones.py,dinov2/hub/utils.pydinov2/models/__init__.py,dinov2/models/vision_transformer.pydinov2/layers/__init__.pyand the 7 layer files it imports
Training, evaluation, segmentation, depth, classifiers, cell-dino, xray-dino, and dinotxt code paths are not included.
How it is loaded
AddaxAI calls:
torch.hub.load(model_dir, model_arch, source="local", pretrained=False)
where model_dir is the local directory the weights and these source files have been downloaded into via the Hugging Face Hub.
License and provenance
DINOv2 is licensed under Apache 2.0. The original code lives at https://github.com/facebookresearch/dinov2. See the LICENSE file for the full text. No source-level modifications have been made to the vendored files except for hubconf.py, which was slimmed to only re-export the three entry points AddaxAI uses.