Gen 3, CURRENT. The loss gradient reaches source tokens through Vφ, ξ and the exchange field. Gen 2 is kept, in its own collection, for the record.
-
dimitarpg13/semsimula-ladder-live-owt-d384-l4-none
Text Generation • Updated • 642 -
dimitarpg13/semsimula-ladder-live-owt-d384-l2-attention-potential-rfqk
Text Generation • Updated • 245 -
dimitarpg13/semsimula-ladder-live-owt-d384-l2-none
Text Generation • Updated • 561 -
dimitarpg13/semsimula-ladder-live-owt-d384-l2-attention-potential
Text Generation • Updated • 483