RSS Bot@lemmy.bestiver.seMB to Hacker News@lemmy.bestiver.seEnglish · 6 days agoOLMo – a fully open LLM outperforming GPT 4o miniallenai.orgexternal-linkmessage-square2fedilinkarrow-up124arrow-down11file-text
arrow-up123arrow-down1external-linkOLMo – a fully open LLM outperforming GPT 4o miniallenai.orgRSS Bot@lemmy.bestiver.seMB to Hacker News@lemmy.bestiver.seEnglish · 6 days agomessage-square2fedilinkfile-text
minus-squarePennomi@lemmy.worldlinkfedilinkEnglisharrow-up7·6 days agoFully open is extremely good, it uses entirely open datasets and has all training and inference code. We need more things like that.
Fully open is extremely good, it uses entirely open datasets and has all training and inference code. We need more things like that.