noneabove1182@sh.itjust.worksM to LocalLLaMA@sh.itjust.worksEnglish · 1 year agoMicrosoft makes new 1.3B coding LLM that outperforms all models on MBPP except GPT-4, reaches third place on HumanEval above GPT-3.5, and shows emergent propertiesarxiv.orgexternal-linkmessage-square2fedilinkarrow-up131arrow-down11
arrow-up130arrow-down1external-linkMicrosoft makes new 1.3B coding LLM that outperforms all models on MBPP except GPT-4, reaches third place on HumanEval above GPT-3.5, and shows emergent propertiesarxiv.orgnoneabove1182@sh.itjust.worksM to LocalLLaMA@sh.itjust.worksEnglish · 1 year agomessage-square2fedilink
minus-squarenoneabove1182@sh.itjust.worksOPMlinkfedilinkEnglisharrow-up2·1 year agoHaven’t seen it yet but hoping it does go up
Haven’t seen it yet but hoping it does go up