DINOv2 ViT-L/14 (RLX meta layout)

DINOv2 ViT-L/14 with HF + RLX meta-key safetensors.

Field Value
Hub id eugenehp/dinov2
Kind Converted / re-laid-out for RLX from an upstream checkpoint.
RLX crate rlx-dinov2
Upstream https://huggingface.co/facebook/dinov2-large

Quick start

hf download eugenehp/dinov2 --local-dir .
cargo run -p rlx-dinov2 --release -- --weights dinov2_vitl14.meta.safetensors --image photo.jpg

Contents

dinov2_vitl14.safetensors (HF keys) and dinov2_vitl14.meta.safetensors (RLX meta layout).

Do not use as the main runtime pack

These files may be present for historical / staging reasons but are not the supported RLX load path:

  • dinov2.f16.gguf

Community *.f16.gguf / LM-only Q4 packs are format wraps โ€” they are not drop-in replacements for the RLX primary file above.

Run with RLX

Clone rlx-models, place this repo under weights/vision/dinov2 (or pass the path explicitly), then:

cargo run -p rlx-dinov2 --release -- --weights dinov2_vitl14.meta.safetensors --image photo.jpg

License

Apache License 2.0 โ€” see LICENSE. Inherit upstream terms when redistributing.

Original weights and authorship: https://huggingface.co/facebook/dinov2-large

Maintenance

Cards and LFS attrs are regenerated from the local weights/ tree in rlx-models via python3 scripts/prepare_weights_hf.py.

Downloads last month
13
GGUF
Model size
0.6B params
Architecture
rlx-dinov2
Hardware compatibility
Log In to add your hardware

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support