lidd1ejimmy@lemmy.ml to Memes@lemmy.mlEnglish · 4 months agoOffline version of Chat GPTlemmy.mlexternal-linkmessage-square27fedilinkarrow-up1500arrow-down18
arrow-up1492arrow-down1external-linkOffline version of Chat GPTlemmy.mllidd1ejimmy@lemmy.ml to Memes@lemmy.mlEnglish · 4 months agomessage-square27fedilink
minus-squareNaz@sh.itjust.workslinkfedilinkarrow-up16·4 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-squarecurbstickle@lemmy.dbzer0.comlinkfedilinkarrow-up13·4 months agollama 3 8b, phi 3 mini, Mistral, moondream 2, neural chat, starling, code llama, llama 2 uncensored, and llava would fit.
minus-squareBudgetBandit@sh.itjust.workslinkfedilinkarrow-up1·4 months agoJust interested in the topic did you 🔨 offline privately?
minus-squarecurbstickle@lemmy.dbzer0.comlinkfedilinkarrow-up1·4 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