transformers
d3d835d4 - [qwen] refactor attentions for vision/audio (#38930)

Commit

188 days ago

[qwen] refactor attentions for vision/audio (#38930) * refactor attentions in vision/audio * remove fa2 import * make config the only args * pass along kwargs from modality encoders * style

References

#38930 - [qwen] refactor attentions for vision/audio

#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

zucchini-nlp

Parents

2e4c0455

transformers d3d835d4 - [qwen] refactor attentions for vision/audio (#38930)

transformers
d3d835d4 - [qwen] refactor attentions for vision/audio (#38930)