LEAP
PublicLEAP: Linear Explainable Attention in Parallel for causal language modeling with O(1) path length, and O(1) inference
additive-attentionattention-mechanismdeep-learningdot-product-attentionlinear-attentionlocal-attentionparallelpytorchrnnsoftmax
Creat:2022-07-02T06:33:21
Update:2025-03-25T13:38:55
4
Stars
0
Stars Increase