☆ Yσɠƚԋσʂ ☆@lemmy.ml to Memes@lemmy.mlEnglish · 23 hours agoBased if truelemmy.mlimagemessage-square8fedilinkarrow-up192arrow-down15
arrow-up187arrow-down1imageBased if truelemmy.ml☆ Yσɠƚԋσʂ ☆@lemmy.ml to Memes@lemmy.mlEnglish · 23 hours agomessage-square8fedilink
minus-squareExotiqueMatter@lemmygrad.mllinkfedilinkarrow-up5·3 hours agoAlmost surely false. I seriously doubt it’s possible to train a modern multy-billions parameters LLM with less than 2 dozen million prompts, even if it’s 16M each, let alone if it’s 16M combined.
minus-square☆ Yσɠƚԋσʂ ☆@lemmy.mlOPlinkfedilinkarrow-up4·3 hours agoyeah I’m very skeptical here as well
Almost surely false. I seriously doubt it’s possible to train a modern multy-billions parameters LLM with less than 2 dozen million prompts, even if it’s 16M each, let alone if it’s 16M combined.
yeah I’m very skeptical here as well