Add SwiftFormer

[shehanmunasinghe]

Model description

'SwiftFormer' paper introduces a novel efficient additive attention mechanism that effectively replaces the quadratic matrix multiplication operations in the self-attention computation with linear element-wise multiplications. A series of models called 'SwiftFormer' is built based on this, which achieves state-of-the-art performance in terms of both accuracy and mobile inference speed. Even their small variant achieves 78.5% top-1 ImageNet1K accuracy with only 0.8 ms latency on iPhone 14, which is more accurate and 2× faster compared to MobileViT-v2.

I would like to add this model to Huggingface.

Open source status

• The model implementation is available
• The model weights are available

Provide useful links for the implementation

Paper: https://arxiv.org/abs/2303.15446
Original code and weights: https://github.com/Amshaker/SwiftFormer
Author: @Amshaker