minus-squaremorrowind@lemm.eetoLocalLLaMA@sh.itjust.works•Qwen/QwQ-32B · Hugging FacelinkfedilinkEnglisharrow-up2·9 hours agoIt matches R1 in the given benchmarks. R1 has 671B params (36 activated) while this only has 32 linkfedilink
minus-squaremorrowind@lemm.eetoLocalLLaMA@sh.itjust.works•Qwen/QwQ-32B · Hugging FacelinkfedilinkEnglisharrow-up2·19 hours agoinsane, absolutely insane linkfedilink
morrowind@lemm.ee to LocalLLaMA@sh.itjust.worksEnglish · 3 days agoChain of Draft: Thinking Faster by Writing Lessplus-squarearxiv.orgexternal-linkmessage-square0fedilinkarrow-up19arrow-down11
arrow-up18arrow-down1external-linkChain of Draft: Thinking Faster by Writing Lessplus-squarearxiv.orgmorrowind@lemm.ee to LocalLLaMA@sh.itjust.worksEnglish · 3 days agomessage-square0fedilink
morrowind@lemm.ee to LocalLLaMA@sh.itjust.worksEnglish · 4 days agoAtom of Thoughts (AOT): lifts gpt-4o-mini to 80.6% F1 on HotpotQA, surpassing o3-mini and DeepSeek-R1plus-squarebsky.appexternal-linkmessage-square0fedilinkarrow-up113arrow-down12
arrow-up111arrow-down1external-linkAtom of Thoughts (AOT): lifts gpt-4o-mini to 80.6% F1 on HotpotQA, surpassing o3-mini and DeepSeek-R1plus-squarebsky.appmorrowind@lemm.ee to LocalLLaMA@sh.itjust.worksEnglish · 4 days agomessage-square0fedilink
minus-squaremorrowind@lemm.eetoTechnology@lemmy.world•Alibaba Releases Advanced Open Video Model, Immediately Becomes AI Porn MachinelinkfedilinkEnglisharrow-up6·6 days agogood luck trying to run a video model locally Unless you have top tier hardware linkfedilink
It matches R1 in the given benchmarks. R1 has 671B params (36 activated) while this only has 32