transformers
280a811e - Use `AlbertConverter` for FNet instead of using FNet's own converter (#14365)

Commit

4 years ago

Use `AlbertConverter` for FNet instead of using FNet's own converter (#14365) * Add normalizer to FNetConverter * Style * Directly use AlbertConverter

References

#14365 - Use `AlbertConverter` for FNet instead of using FNet's own converter

#15748 - Fix segformer reshape last stage

#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

qqaatw

Parents

55f49c5f

transformers 280a811e - Use `AlbertConverter` for FNet instead of using FNet's own converter (#14365)

transformers
280a811e - Use `AlbertConverter` for FNet instead of using FNet's own converter (#14365)