DINOv2 ViT-B/14 with registers, pretrained backbone (mirror)

Byte-identical mirror of facebookresearch/dinov2, checkpoint served from dl.fbaipublicfiles.com for the Cuvis.AI plugins. No fine-tuning, conversion or re-serialization: the files below are the upstream release as published, with the upstream licence text in LICENSE.

Why this mirror exists

Cuvis.AI provisions model weights once into a shared cache (download-model download <name> from cuvis-ai-core) and then runs its pipelines in an offline, token-free runtime that only reads that cache. Hosting the exact upstream files under the cubert-gmbh organisation makes that provisioning reproducible (commit-pinned and sha256-verified) and takes the per-user Hugging Face account and token out of the users' path.

Files and provenance

File	Upstream source	Upstream revision / id	sha256	Size
dinov2_vitb14_reg4_pretrain.pth	https://dl.fbaipublicfiles.com/dinov2/dinov2_vitb14/dinov2_vitb14_reg4_pretrain.pth	n/a (URL; sha256 pinned)	73182a088cf94833c94b1666d1c99e02fe87e2007bff57b564fb6206e25dba71	346.4 MB
LICENSE	https://raw.githubusercontent.com/facebookresearch/dinov2/main/LICENSE	n/a (URL; sha256 pinned)	600cc67cc4cb2f5ea317dcfc687ad1c74dc4bec8782bbe9db0afd83513b935b7	11.4 kB

Mirrored on 2026-09-04 by Cubert GmbH from the sources above. The sha256 values are the upstream values; tools/mirror_weights.py check in cuvis-ai-core re-verifies this repository against them and against the upstream licence text.

Licence

Apache License 2.0. The LICENSE file is the upstream licence text taken verbatim from https://github.com/facebookresearch/dinov2 at the mirror date. Copyright remains with the upstream authors; Cubert GmbH claims no rights in these files.

Usage with Cuvis.AI

uv run download-model download dinov2_vitb14_reg4

download-model (from cuvis-ai-core) provisions the file into the shared Hugging Face cache and verifies its sha256. From cuvis-ai-core 0.16.0 on, ModelWeights.resolve("<name>") returns the cached path and the cuvis-ai-dinomaly nodes resolve their weights through it, so a pipeline needs no manual step once the weights are provisioned; earlier plugin releases still fetch from their original upstream sources.