AvitoTech

/

CLIP-ViT-base-for-animal-identification

like 1

Follow

AvitoTech 122

Hi, and thanks for releasing these models.

This follows up on the report on the SigLIP2-Base repo.

• Loading already worked here -- CLIPModel.base_model_prefix happens to be "clip", so the published prefix is stripped on load. config.json and model.safetensors are therefore not touched by this PR.
• Image processor. Added preprocessor_config.json, copied unchanged from openai/clip-vit-base-patch32, so the repo is self-contained and the card no longer has to send users to another repository for preprocessing.
• License. Added license: apache-2.0 and a LICENSE file (see below).

Verification

The reference is the wrapper this checkpoint was trained with: it is built from
openai/clip-vit-base-patch32 and loaded from the published model.safetensors with
load_state_dict(strict=True) (0 missing / 0 unexpected keys). Its embeddings are then
compared against AutoModel.from_pretrained on the files in this PR.

No weight values change anywhere in this PR.

One more thing worth flagging

Comparing these weights against the base model, the fine-tune moved only vision blocks 7-11;
the text tower, both projection heads and logit_scale/logit_bias are byte-identical to
openai/clip-vit-base-patch32. The two towers are therefore no longer aligned, and image-text scoring gives
wrong answers (on a COCO cat photo the model now ranks "a photo of a car" above
"a photo of two cats"). That is expected for a triplet-loss re-identification fine-tune, but
nothing said so, and the Hub still advertises a zero-shot-image-classification tag.

For that reason this PR adds only preprocessor_config.json and deliberately does not
add tokenizer files -- shipping them would make that broken path runnable straight from the
repo. Mentioning it here rather than editing the card, since that is your call to make.

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.