transformers
9719202d - Generate: fix `SinkCache` on Llama models (#30581)

Commit

1 year ago

Generate: fix `SinkCache` on Llama models (#30581)

References

#29969 - [SigLIP] Add fast tokenizer

#30581 - Generate: fix `SinkCache` on Llama models

#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

#62 - Add initial DEIMv2 model implementation

#65 - Fix RTDetrV2 sine position embedding ordering

Author

gante

gante

Parents

Loading