ThelastfingerofH to LocalLLaMA@sh.itjust.worksEnglish · 3 days agoMythos-class model on huggingface: 14T parametershuggingface.coexternal-linkmessage-square12linkfedilinkarrow-up128arrow-down19cross-posted to: [email protected]
arrow-up119arrow-down1external-linkMythos-class model on huggingface: 14T parametershuggingface.coThelastfingerofH to LocalLLaMA@sh.itjust.worksEnglish · 3 days agomessage-square12linkfedilinkcross-posted to: [email protected]
minus-squareThelastfingerofHOPlinkfedilinkEnglisharrow-up2·2 days agoThis is also like the reason why Nvidia markets the nvl72 rack as being able to train 10t parameter models, because closed ai companies already do it with 1 or two racks. Maybe 20t parameter models with 2 racks.
This is also like the reason why Nvidia markets the nvl72 rack as being able to train 10t parameter models, because closed ai companies already do it with 1 or two racks. Maybe 20t parameter models with 2 racks.