transformers
fe4197ab - [Generate] Remove attention_mask and integrate model_main_input_name (#14856)

Commit

4 years ago

[Generate] Remove attention_mask and integrate model_main_input_name (#14856) * up * save * correct * up * correct more * up * up * up * up * up * correct * fix tf * fix * remove tokenizer

References

#14856 - [Generate] Remove attention_mask and integrate model_main_input_name

#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

#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

patrickvonplaten

Parents

86b40073

transformers fe4197ab - [Generate] Remove attention_mask and integrate model_main_input_name (#14856)

transformers
fe4197ab - [Generate] Remove attention_mask and integrate model_main_input_name (#14856)