cm0002@literature.cafe to AI - Artificial intelligence@programming.devEnglish · 4 months agoTiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5Bhuggingface.coexternal-linkmessage-square3linkfedilinkarrow-up16arrow-down11file-textcross-posted to: technology@lemmy.ziptechnology@lemmygrad.mltechnology@lemmy.ml
arrow-up15arrow-down1external-linkTiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5Bhuggingface.cocm0002@literature.cafe to AI - Artificial intelligence@programming.devEnglish · 4 months agomessage-square3linkfedilinkfile-textcross-posted to: technology@lemmy.ziptechnology@lemmygrad.mltechnology@lemmy.ml
minus-squarehumanspiral@lemmy.calinkfedilinkEnglisharrow-up1·3 months agoSeems very poor at understanding anything new. As in it doesn’t even try to accept corrections. gemma 1b is bad too, but at least it tries. Could this be related to ollama not implementing special algorithm it uses?
Seems very poor at understanding anything new. As in it doesn’t even try to accept corrections. gemma 1b is bad too, but at least it tries. Could this be related to ollama not implementing special algorithm it uses?