simple@lemmy.world to Technology@lemmy.ml · 3 years agoMicrosoft Releases 1.3 Bn Parameter Language Model, Outperforms LLaMaanalyticsindiamag.comexternal-linkmessage-square1linkfedilinkarrow-up13arrow-down11file-textcross-posted to: technology@lemmy.world
arrow-up12arrow-down1external-linkMicrosoft Releases 1.3 Bn Parameter Language Model, Outperforms LLaMaanalyticsindiamag.comsimple@lemmy.world to Technology@lemmy.ml · 3 years agomessage-square1linkfedilinkfile-textcross-posted to: technology@lemmy.world
I wonder if higher quality datasets are the future rather than using tons of internet scraped texts. Either way, neat model!
minus-squareBehohippy@lemmy.worldlinkfedilinkarrow-up1·3 years agoBad article title. This is the “Textbooks are all you need” paper from a few days ago. It’s programming focused and I think Python only. For general purpose LLM use, LLaMA is still better.
Bad article title. This is the “Textbooks are all you need” paper from a few days ago. It’s programming focused and I think Python only. For general purpose LLM use, LLaMA is still better.