transformers
170fcaa6 - Generalize decay_mask_fn to apply mask to all LayerNorm params (#18273)

Commit

3 years ago

Generalize decay_mask_fn to apply mask to all LayerNorm params (#18273) * generalize decay_mask_fn to find all layernorm params * fixup * generalising decay_mask_fn

References

#18273 - Generalize decay_mask_fn to apply mask to all LayerNorm params

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

#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

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

#41212 - Add EoMT with DINOv3 backbone

#62 - Add initial DEIMv2 model implementation

Author

duongna21

Parents

83d2d745

transformers 170fcaa6 - Generalize decay_mask_fn to apply mask to all LayerNorm params (#18273)

transformers
170fcaa6 - Generalize decay_mask_fn to apply mask to all LayerNorm params (#18273)