|
Download README.md from cubert-gmbh/steervit: direct link, hf CLI and curl.
- Browser
- Download file 2.76 kB
-
https://huggingface.co/cubert-gmbh/steervit/resolve/main/README.md
- Command line
-
hf download hf://cubert-gmbh/steervit/README.md
-
curl -L -o README.md https://huggingface.co/cubert-gmbh/steervit/resolve/main/README.md
2.76 kB
| license: apache-2.0 | |
| base_model: JonaRuthardt/SteerViT | |
| tags: | |
| - mirror | |
| - cuvis-ai | |
| - steervit | |
| - vision-transformer | |
| - image-feature-extraction | |
| # SteerViT, DINOv2 base checkpoint (mirror) | |
| Byte-identical mirror of [`JonaRuthardt/SteerViT`](https://huggingface.co/JonaRuthardt/SteerViT) at revision `4468b69138d397fd329df00e80093387c26c77b2` (code: <https://github.com/manugaurdl/SteerViT>) for the | |
| [Cuvis.AI](https://github.com/cubert-hyperspectral/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 | | |
| |---|---|---|---|---| | |
| | `steervit_dinov2_base.pth` | `JonaRuthardt/SteerViT` / `steervit_dinov2_base.pth` | `4468b69138d397fd329df00e80093387c26c77b2` | `3ee74e5fba5cdbcbbdc35042b59fc44d54a68864724186c0ba4f5e2174892e3a` | 92.8 MB | | |
| | `LICENSE` | <https://www.apache.org/licenses/LICENSE-2.0.txt> | n/a (URL; sha256 pinned) | `cfc7749b96f63bd31c3c42b5c471bf756814053e847c10f3eb003417bc523d30` | 11.4 kB | | |
| Mirrored on 2026-10-09 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://www.apache.org/licenses/LICENSE-2.0.txt> (the upstream Hugging Face repository declares `license: apache-2.0` for its checkpoints and ships no LICENSE file; the SteerViT code on GitHub declares the MIT License) at the mirror date. Copyright remains with the upstream authors; Cubert | |
| GmbH claims no rights in these files. | |
| ## Usage with Cuvis.AI | |
| ```text | |
| uv run download-model download steervit_dinov2_base | |
| ``` | |
| `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-steervit` 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. | |