minus-squaremorrowind@lemm.eeOPtoLocalLLaMA@sh.itjust.works•EXAONE Deep ━ Setting a New Standard for Reasoning AI - LG AI Research NewslinkfedilinkEnglisharrow-up1·2 days agowhat is the license? The link on hf just 404s linkfedilink
morrowind@lemm.ee to LocalLLaMA@sh.itjust.worksEnglish · 2 days agoEXAONE Deep ━ Setting a New Standard for Reasoning AI - LG AI Research Newsplus-squarewww.lgresearch.aiexternal-linkmessage-square4fedilinkarrow-up13
arrow-up13external-linkEXAONE Deep ━ Setting a New Standard for Reasoning AI - LG AI Research Newsplus-squarewww.lgresearch.aimorrowind@lemm.ee to LocalLLaMA@sh.itjust.worksEnglish · 2 days agomessage-square4fedilink
minus-squaremorrowind@lemm.eeOPtoLocalLLaMA@sh.itjust.works•Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired SketchinglinkfedilinkEnglisharrow-up2·3 days agoVery similar to chain of draft but seems more thorough linkfedilink
morrowind@lemm.ee to LocalLLaMA@sh.itjust.worksEnglish · 3 days agoSketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketchingplus-squarearxiv.orgexternal-linkmessage-square2fedilinkarrow-up111
arrow-up111external-linkSketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketchingplus-squarearxiv.orgmorrowind@lemm.ee to LocalLLaMA@sh.itjust.worksEnglish · 3 days agomessage-square2fedilink
morrowind@lemm.ee to LocalLLaMA@sh.itjust.worksEnglish · 8 days agoSorting-Free GPU Kernels for LLM Samplingplus-squareflashinfer.aiexternal-linkmessage-square0fedilinkarrow-up15
arrow-up15external-linkSorting-Free GPU Kernels for LLM Samplingplus-squareflashinfer.aimorrowind@lemm.ee to LocalLLaMA@sh.itjust.worksEnglish · 8 days agomessage-square0fedilink
minus-squaremorrowind@lemm.eeOPtoLocalLLaMA@sh.itjust.works•Reka Flash, open source 21B model comparable to QWQ 32BlinkfedilinkEnglisharrow-up2·edit-28 days agoMore info here https://www.reka.ai/news/introducing-reka-flash HF: https://huggingface.co/RekaAI/reka-flash-3 linkfedilink
morrowind@lemm.ee to LocalLLaMA@sh.itjust.worksEnglish · 8 days agoReka Flash, open source 21B model comparable to QWQ 32Bi.postimg.ccimagemessage-square2fedilinkarrow-up118
arrow-up118imageReka Flash, open source 21B model comparable to QWQ 32Bi.postimg.ccmorrowind@lemm.ee to LocalLLaMA@sh.itjust.worksEnglish · 8 days agomessage-square2fedilink
minus-squaremorrowind@lemm.eetoLocalLLaMA@sh.itjust.works•Qwen/QwQ-32B · Hugging FacelinkfedilinkEnglisharrow-up3·14 days 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-up2·14 days agoinsane, absolutely insane linkfedilink
morrowind@lemm.ee to LocalLLaMA@sh.itjust.worksEnglish · 16 days agoChain of Draft: Thinking Faster by Writing Lessplus-squarearxiv.orgexternal-linkmessage-square0fedilinkarrow-up18
arrow-up18external-linkChain of Draft: Thinking Faster by Writing Lessplus-squarearxiv.orgmorrowind@lemm.ee to LocalLLaMA@sh.itjust.worksEnglish · 16 days agomessage-square0fedilink
morrowind@lemm.ee to LocalLLaMA@sh.itjust.worksEnglish · 17 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-up113
arrow-up113external-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 · 17 days agomessage-square0fedilink
what is the license? The link on hf just 404s