| # NOTICE — vision-encoder | |
| The weights in this directory (`backbone/` and `projection.safetensors`) are DINOv3 by | |
| Meta Platforms, Inc. or derivative works of it made by Vast AI. They are distributed under | |
| the DINOv3 License (see `LICENSE.md` here and in `backbone/`), not under the Apache 2.0 | |
| license that covers the rest of this repository. Use must comply with that license, | |
| including its trade-control and prohibited-use terms. Research publications that use these | |
| weights must acknowledge the use of DINOv3. | |