Equimo

What's Changed
* Add support for DyT by clementpoiret in https://github.com/clementpoiret/Equimo/pull/11
* feat(vit): allow passing kwargs to blocks by clementpoiret in https://github.com/clementpoiret/Equimo/pull/12


**Full Changelog**: https://github.com/clementpoiret/Equimo/compare/v0.3.0...v0.3.3

This release adds support for text embedding support. It adds a text-compatible transformer and a tokenizer (from tensorflow_text). This enables many workflows when working on both images and text.

The first compatible model is TIPS. SigLIP2 text will come later.

What's Changed
* Experimental text embedding support by clementpoiret in https://github.com/clementpoiret/Equimo/pull/10


**Full Changelog**: https://github.com/clementpoiret/Equimo/compare/v0.2.4...v0.3.0

What's Changed
* feat(tips): add pretrained weights by clementpoiret in https://github.com/clementpoiret/Equimo/pull/9


**Full Changelog**: https://github.com/clementpoiret/Equimo/compare/v0.2.3...v0.2.4

What's Changed
* Add support for SigLIP 2 without NaFlex by clementpoiret in https://github.com/clementpoiret/Equimo/pull/8
* Add support for loading torch models from timm
* Add support for serializing act functions (required to load some SigLIP models)
* Allows passing kwargs to load_model to override saved metadata

**Full Changelog**: https://github.com/clementpoiret/Equimo/compare/v0.2.2...v0.2.3

What's Changed
* fix(io): missing cache dir by clementpoiret in https://github.com/clementpoiret/Equimo/pull/7


**Full Changelog**: https://github.com/clementpoiret/Equimo/compare/v0.2.1...v0.2.2

Dinov2 Giant can now be loaded correctly using:

python
from equimo.io import load_model

model = load_model(cls="vit", identifier="dinov2_vitg14_reg")


What's Changed
* feat(vit): add support for loading dinov2 giant by clementpoiret in https://github.com/clementpoiret/Equimo/pull/5


**Full Changelog**: https://github.com/clementpoiret/Equimo/compare/v0.2.0...v0.2.1