sanitation@lemmy.today to Technology@lemmy.worldEnglish · 3 days agoIf open weight models are the future, U.S. AI companies are going to have a hard timewww.fastcompany.comexternal-linkmessage-square88linkfedilinkarrow-up1283arrow-down12
arrow-up1281arrow-down1external-linkIf open weight models are the future, U.S. AI companies are going to have a hard timewww.fastcompany.comsanitation@lemmy.today to Technology@lemmy.worldEnglish · 3 days agomessage-square88linkfedilink
minus-squareMwa@thelemmy.clublinkfedilinkEnglisharrow-up4·2 days agoWe even got open weight models that’s 27B + 1-bit (and it still has good performance)
minus-squarebrucethemoose@lemmy.worldlinkfedilinkEnglisharrow-up3·2 days agoBonsai? Or whatever it’s called? It’s a con, so far; it’s not better than smaller models quantized to 3-4 bits. I love, love the idea of bitnet, but it only seems to work with models trained from scratch, which no one has done at scale yet.
We even got open weight models that’s 27B + 1-bit (and it still has good performance)
Bonsai? Or whatever it’s called? It’s a con, so far; it’s not better than smaller models quantized to 3-4 bits.
I love, love the idea of bitnet, but it only seems to work with models trained from scratch, which no one has done at scale yet.
yeah bonsai