transformers
b090b790 - Make Swin work with VisionEncoderDecoderModel (#15527)

Commit

3 years ago

Make Swin work with VisionEncoderDecoderModel (#15527) * Add attribute_map * Add mention in docs * Set hidden_size attribute correctly * Add note about Transformer-based models only Co-authored-by: Niels Rogge <nielsrogge@Nielss-MBP.localdomain>

References

#62 - Add initial DEIMv2 model implementation

#58 - Add EoMT DINOv3 model

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

#27720 - Add common processor tests

#32831 - [Docs] Update resources

#29969 - [SigLIP] Add fast tokenizer

#41212 - Add EoMT with DINOv3 backbone

#39821 - Support MetaCLIP 2

#15748 - Fix segformer reshape last stage

#33111 - [Backbone] Remove out_features everywhere

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

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

#15527 - Make Swin work with VisionEncoderDecoderModel

Author

NielsRogge

Parents

ec15da24

transformers b090b790 - Make Swin work with VisionEncoderDecoderModel (#15527)

transformers
b090b790 - Make Swin work with VisionEncoderDecoderModel (#15527)