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

Commit

316 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

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

#62 - Add initial DEIMv2 model implementation

#65 - Fix RTDetrV2 sine position embedding ordering

#44375 - Add RF-DETR

#71 - Use Mask2Former ignore_value in mask matching and losses

#44385 - Fix make check-repo

#45082 - [VidEoMT] Update conversion script

#45110 - Add SAM 3.1

Author

zucchini-nlp

Parents

2e4c0455

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

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