Shatter: An Efficient Transformer Encoder with Single-Headed Self-Attention and Relative Sequence Partitioning

Add code
Aug 30, 2021
Figure 1 for Shatter: An Efficient Transformer Encoder with Single-Headed Self-Attention and Relative Sequence Partitioning
Figure 2 for Shatter: An Efficient Transformer Encoder with Single-Headed Self-Attention and Relative Sequence Partitioning
Figure 3 for Shatter: An Efficient Transformer Encoder with Single-Headed Self-Attention and Relative Sequence Partitioning
Figure 4 for Shatter: An Efficient Transformer Encoder with Single-Headed Self-Attention and Relative Sequence Partitioning

Share this with someone who'll enjoy it:

View paper onarxiv icon

Share this with someone who'll enjoy it: