transformers
83f9314d - fix: cast input pixels to appropriate dtype for image_to_text pipelines (#24947)

Commit

2 years ago

fix: cast input pixels to appropriate dtype for image_to_text pipelines (#24947) * fix: cast input pixels to appropriate dtype for image_to_text tasks * fix: add casting to pixel inputs of additional models after running copy checks

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

#33111 - [Backbone] Remove out_features everywhere

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

#24947 - fix: cast input pixels to appropriate dtype for image_to_text pipelines

Author

JimAllanson

Parents

1c7e5e23

transformers 83f9314d - fix: cast input pixels to appropriate dtype for image_to_text pipelines (#24947)

transformers
83f9314d - fix: cast input pixels to appropriate dtype for image_to_text pipelines (#24947)