Fix AutoModel loading, add image processor and Apache-2.0 license
Hi, and thanks for releasing these models.
This follows up on the report on the SigLIP2-Base repo.
AutoModel.from_pretraineddid not work. Every tensor was stored under abackbone.prefix left over from the training wrapper, which does not matchDinov2Model.base_model_prefix, so all 223 parameters were randomly initialised and only a warning was emitted. The tensors are now stored under their canonical names.config.json.image_size:518.- Image processor. Added
preprocessor_config.json, copied unchanged fromfacebook/dinov2-small, so the repo is self-contained and the card no longer has to send users to another repository for preprocessing. - License. Added
license: apache-2.0and aLICENSEfile (see below).
Verification
The reference is the wrapper this checkpoint was trained with: it is built fromfacebook/dinov2-small and loaded from the published model.safetensors withload_state_dict(strict=True) (0 missing / 0 unexpected keys). Its embeddings are then
compared against AutoModel.from_pretrained on the files in this PR.
| check | result |
|---|---|
| missing / unexpected / mismatched keys | 0 / 0 / 0 |
| max abs difference vs. that reference | 0.0 |
| embedding dimensionality | 384 |
image processor output vs. facebook/dinov2-small |
identical (max abs diff 0.0) |
No weight values change anywhere in this PR -- only tensor names, config.json and the card.
About the license
The repository currently has no license field and no LICENSE file, which is what prompted
the original question. This PR proposes Apache-2.0, matching the other public AvitoTech
models on the Hub and the Apache-2.0 base model(s) this is derived from -- but that call is
yours. If you would rather use different terms, say so and I will amend the PR; if you would
rather add the license yourself, feel free to drop the LICENSE file and the frontmatter
line from this PR and take just the loading fix.