Gen 3, CURRENT. The loss gradient reaches source tokens through Vφ, ξ and the exchange field; forward pass identical to Gen 2.
-
dimitarpg13/semsimula-ladder-live-owt-d384-l4-none
Text Generation • Updated • 609 -
dimitarpg13/semsimula-ladder-live-owt-d384-l2-none
Text Generation • Updated • 528 -
dimitarpg13/semsimula-ladder-live-owt-d384-l2-attention-potential
Text Generation • Updated • 443 -
dimitarpg13/semsimula-ladder-live-owt-d384-l2-attention-potential-rfqk
Text Generation • Updated • 220