schizoidman@lemm.ee to Technology@lemmy.worldEnglish · 10 days agoApple to use Chinese giant Alibaba’s AI in iPhoneswww.semafor.comexternal-linkmessage-square20fedilinkarrow-up1112arrow-down18file-text
arrow-up1104arrow-down1external-linkApple to use Chinese giant Alibaba’s AI in iPhoneswww.semafor.comschizoidman@lemm.ee to Technology@lemmy.worldEnglish · 10 days agomessage-square20fedilinkfile-text
minus-squarebrucethemoose@lemmy.worldlinkfedilinkEnglisharrow-up1·10 days agoSome of the distillations are trained on top of Qwen 2.5. And for some cases, FuseAI (a special merge of several thinking models), Qwen Coder, EVA-Gutenberg Qwen, or some other specialized models do a better job than Deepseek 32B in certain niches.
Some of the distillations are trained on top of Qwen 2.5.
And for some cases, FuseAI (a special merge of several thinking models), Qwen Coder, EVA-Gutenberg Qwen, or some other specialized models do a better job than Deepseek 32B in certain niches.