transformers
ae6a7a76 - Use CLIP model config to set some kwargs for components (#16609)

Commit

3 years ago

Use CLIP model config to set some kwargs for components (#16609) * Use CLIP model's config for some fields (if specified) instead of those of vision & text components. Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>

References

#16609 - Use CLIP model config to set some kwargs for components

#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

#58 - Add EoMT DINOv3 model

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

#41212 - Add EoMT with DINOv3 backbone

#62 - Add initial DEIMv2 model implementation

Author

ydshieh

Parents

47c5c059

transformers ae6a7a76 - Use CLIP model config to set some kwargs for components (#16609)

transformers
ae6a7a76 - Use CLIP model config to set some kwargs for components (#16609)