transformers
e768616a - Fix load balancing loss func for mixtral (#28256)

Commit

1 year ago

Fix load balancing loss func for mixtral (#28256) * Correct the implementation of auxiliary loss of mixtrtal * correct the implementation of auxiliary loss of mixtrtal * Implement a simpler calculation method --------- Co-authored-by: zhangliangxu3 <zhangliangxu3@jd.com>

References

#28256 - Fix load balancing loss func for mixtral

#29969 - [SigLIP] Add fast tokenizer

#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

liangxuZhang

Parents

5d4d62d0

transformers e768616a - Fix load balancing loss func for mixtral (#28256)

transformers
e768616a - Fix load balancing loss func for mixtral (#28256)