A standard transformer architecture, showing on the left an encoder, and on the right a decoder. Note: this uses the pre-LN convention, which is different from the post-LN convention used in the original 2017 transformer.
(echo:: @ ᯤ)
A standard transformer architecture, showing on the left an encoder, and on the right a decoder. Note: this uses the pre-LN convention, which is different from the post-LN convention used in the original 2017 transformer.
(echo:: @ ᯤ)