@pavnilschandaM to AI Companions • 10 months ago[Resource] Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"github.comexternal-linkmessage-square0arrow-up14arrow-down13
arrow-up11arrow-down1external-link[Resource] Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"github.com@pavnilschandaM to AI Companions • 10 months agomessage-square0