pavnilschanda@lemmy.worldcake to Technology@lemmy.worldEnglish · 9 months agoLLMs are surprisingly great at compressing images and audio, DeepMind researchers findventurebeat.comexternal-linkmessage-square12fedilinkarrow-up1102arrow-down15cross-posted to: aicompanions@lemmy.worldtechnology@lemmy.mltech@kbin.social
arrow-up197arrow-down1external-linkLLMs are surprisingly great at compressing images and audio, DeepMind researchers findventurebeat.compavnilschanda@lemmy.worldcake to Technology@lemmy.worldEnglish · 9 months agomessage-square12fedilinkcross-posted to: aicompanions@lemmy.worldtechnology@lemmy.mltech@kbin.social
minus-squareNaibofTabr@infosec.publinkfedilinkEnglisharrow-up9·9 months agoDo you need the dataset to do the compression? Is the trained model not effective on its own?
minus-squareTibert@compuverse.uklinkfedilinkEnglisharrow-up13·9 months agoWell from the article a dataset is required, but not always the heavier one. Tho it doesn’t solve the speed issue, where the llm will take a lot more time to do the compression. gzip can compress 1GB of text in less than a minute on a CPU, an LLM with 3.2 million parameters requires an hour to compress
minus-squarerubikcuber@programming.devcakelinkfedilinkEnglisharrow-up1·9 months agodeleted by creator
Do you need the dataset to do the compression? Is the trained model not effective on its own?
Well from the article a dataset is required, but not always the heavier one.
Tho it doesn’t solve the speed issue, where the llm will take a lot more time to do the compression.
deleted by creator