transformers
d63bdf78 - Add FP32 cast in ConvNext LayerNorm to prevent rounding errors with FP16 input (#18746)

Commit

3 years ago

Add FP32 cast in ConvNext LayerNorm to prevent rounding errors with FP16 input (#18746) * Adding cast to fp32 in convnext layernorm to prevent rounding errors in the case of fp16 input * Trigger CI

References

#62 - Add initial DEIMv2 model implementation

#58 - Add EoMT DINOv3 model

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

#27720 - Add common processor tests

#32831 - [Docs] Update resources

#29969 - [SigLIP] Add fast tokenizer

#41212 - Add EoMT with DINOv3 backbone

#39821 - Support MetaCLIP 2

#33111 - [Backbone] Remove out_features everywhere

#33174 - [Zero-shot image classification pipeline] Remove tokenizer_kwargs

#19449 - [WIP] Fix weights initialization of several vision models

#18746 - Add FP32 cast in ConvNext LayerNorm to prevent rounding errors with FP16 input

Author

jimypbr

Parents

532ca050

transformers d63bdf78 - Add FP32 cast in ConvNext LayerNorm to prevent rounding errors with FP16 input (#18746)

transformers
d63bdf78 - Add FP32 cast in ConvNext LayerNorm to prevent rounding errors with FP16 input (#18746)