0.0.7

multiply by token embedding weight for logits by default

0.0.6

add feedforward GLU variant and scalenorm

0.0.5

expose dim head, show how simple gpt3 is

0.0.4

always fix head dimension at 64, so users do not trip up with imprope…

0.0.3

deploy

0.0.2

complete masking

0.0.1

first commit of full enc/dec