@lidd1ejimmy@lemmy.ml to Memes@lemmy.mlEnglish • 2 months agoOffline version of Chat GPTlemmy.mlimagemessage-square27fedilinkarrow-up1485arrow-down17
arrow-up1478arrow-down1imageOffline version of Chat GPTlemmy.ml@lidd1ejimmy@lemmy.ml to Memes@lemmy.mlEnglish • 2 months agomessage-square27fedilink
minus-square@Naz@sh.itjust.workslinkfedilink16•2 months agosquints That says , “PHILLIPS DVD+R” So we’re looking at a 4.7GB model, or just a hair under the tiniest, most incredibly optimized implementation of <INSERT_MODEL_NAME_HERE>
minus-square@curbstickle@lemmy.dbzer0.comlinkfedilink13•2 months agollama 3 8b, phi 3 mini, Mistral, moondream 2, neural chat, starling, code llama, llama 2 uncensored, and llava would fit.
minus-square@BudgetBandit@sh.itjust.workslinkfedilink1•2 months agoJust interested in the topic did you 🔨 offline privately?
minus-square@curbstickle@lemmy.dbzer0.comlinkfedilink1•2 months agoI’m not an expert on them or anything, but feel free
squints
That says , “PHILLIPS DVD+R”
So we’re looking at a 4.7GB model, or just a hair under the tiniest, most incredibly optimized implementation of <INSERT_MODEL_NAME_HERE>
llama 3 8b, phi 3 mini, Mistral, moondream 2, neural chat, starling, code llama, llama 2 uncensored, and llava would fit.
Just interested in the topic did you 🔨 offline privately?
I’m not an expert on them or anything, but feel free