transformers
e9356a42 - Fix qwen2vl float16 inference bug (#33312)

Commit

1 year ago

Fix qwen2vl float16 inference bug (#33312) * fix qwen2vl float16 inference bug * [run-slow] qwen2_vl

References

#29969 - [SigLIP] Add fast tokenizer

#33312 - Fix qwen2vl float16 inference bug

#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

GeLee-Q

GeLee-Q

Parents

Loading