NoSpotOfGround@lemmy.world to Technology@lemmy.worldEnglish · 9 days agoAlgorithm based on LLMs doubles lossless data compression ratestechxplore.comexternal-linkmessage-square35fedilinkarrow-up1110arrow-down121
arrow-up189arrow-down1external-linkAlgorithm based on LLMs doubles lossless data compression ratestechxplore.comNoSpotOfGround@lemmy.world to Technology@lemmy.worldEnglish · 9 days agomessage-square35fedilink
minus-squareHarlehatschi@lemmy.mllinkfedilinkEnglisharrow-up1·8 days agoBut spending a lot of processing power to gain smaller sizes matters mostly in cases you want to store things long term. You probably wouldn’t want to keep the exact same LLM with the same weightings and stuff around in that case.
But spending a lot of processing power to gain smaller sizes matters mostly in cases you want to store things long term. You probably wouldn’t want to keep the exact same LLM with the same weightings and stuff around in that case.