SoftestSapphic@lemmy.world to 196@lemmy.world · 4 days ago"AI" rulelemmy.worldimagemessage-square79fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1image"AI" rulelemmy.worldSoftestSapphic@lemmy.world to 196@lemmy.world · 4 days agomessage-square79fedilink
minus-squareFooBarrington@lemmy.worldlinkfedilinkarrow-up0·3 days agoThat’s also true, though it’s important to remember that the “experts” aren’t experts in the classical sense. Say you have a word made up of 3 tokens, it’s possible that each token is routed to a different expert. It’s just a model architecture.
That’s also true, though it’s important to remember that the “experts” aren’t experts in the classical sense. Say you have a word made up of 3 tokens, it’s possible that each token is routed to a different expert. It’s just a model architecture.