transformers
aa64f086 - Fix llava next tie_word_embeddings config (#30640)

Commit

1 year ago

Fix llava next tie_word_embeddings config (#30640) * fix llava next embedding * add docstring * Update src/transformers/models/llava_next/configuration_llava_next.py Co-authored-by: NielsRogge <48327001+NielsRogge@users.noreply.github.com> --------- Co-authored-by: NielsRogge <48327001+NielsRogge@users.noreply.github.com>

References

#29969 - [SigLIP] Add fast tokenizer

#30640 - Fix llava next tie_word_embeddings config

#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

SunMarc

Parents

9c772ac8

transformers aa64f086 - Fix llava next tie_word_embeddings config (#30640)

transformers
aa64f086 - Fix llava next tie_word_embeddings config (#30640)