Add LayerScale to NAT/DiNAT (#20325)

Commit

3 years ago

Add LayerScale to NAT/DiNAT (#20325) * Add LayerScale to NAT/DiNAT. Completely dropped the ball on LayerScale in the original PR (#20219). This is just an optional argument in both models, and is only activated for larger variants in order to provide training stability. * Add LayerScale to NAT/DiNAT. Minor error fixed. Co-authored-by: Ali Hassani <ahassanijr@gmail.com>

References

#19449 - [WIP] Fix weights initialization of several vision models

#20325 - Add LayerScale to NAT/DiNAT

#27720 - Add common processor tests

#29969 - [SigLIP] Add fast tokenizer

#32831 - [Docs] Update resources

#33111 - [Backbone] Remove out_features everywhere

#33174 - [Zero-shot image classification pipeline] Remove tokenizer_kwargs

#39821 - Support MetaCLIP 2

#58 - Add EoMT DINOv3 model

#59 - Fix attention mask handling in EoMT-DINOv3 converter

#41212 - Add EoMT with DINOv3 backbone