Destide@feddit.uk to Programming@programming.devEnglish · 3 天前Open-R1: a fully open reproduction of DeepSeek-R1huggingface.coexternal-linkmessage-square9fedilinkarrow-up1107arrow-down15cross-posted to: technology@lemmy.worldtechnology@lemmy.ziphackernews@lemmy.bestiver.se
arrow-up1102arrow-down1external-linkOpen-R1: a fully open reproduction of DeepSeek-R1huggingface.coDestide@feddit.uk to Programming@programming.devEnglish · 3 天前message-square9fedilinkcross-posted to: technology@lemmy.worldtechnology@lemmy.ziphackernews@lemmy.bestiver.se
minus-squaremanicdave@feddit.uklinkfedilinkarrow-up4arrow-down1·3 天前All I want is a 3gb model for the raspberry pi. 7b is too big and 1.5b is too stupid.
minus-squareTomasEkeli@programming.devlinkfedilinkarrow-up4·2 天前honestly both 7b and 8b are pretty dumb as well.
minus-squareMadhuGururajan@programming.devlinkfedilinkEnglisharrow-up1·11 小时前we could add so much deterministic code at 1.5GB that would start religions…
All I want is a 3gb model for the raspberry pi. 7b is too big and 1.5b is too stupid.
3B is probably also pretty dumb
honestly both 7b and 8b are pretty dumb as well.
we could add so much deterministic code at 1.5GB that would start religions…
True