LughMA to FuturologyEnglish · 24 days agoThis new Chinese AI Is outperforming ChatGPT — and its open-source & runs locallywww.tomsguide.comexternal-linkmessage-square16linkfedilinkarrow-up168arrow-down110
arrow-up158arrow-down1external-linkThis new Chinese AI Is outperforming ChatGPT — and its open-source & runs locallywww.tomsguide.comLughMA to FuturologyEnglish · 24 days agomessage-square16linkfedilink
minus-squareFluffy Kitty Cat@slrpnk.netlinkfedilinkEnglisharrow-up3·23 days agoGiven how memory is the bottleneck especially at the very low end it makes me wonder if one bit quantization of an extremely large model would be a gigabyte per gigabyte of ram better
Given how memory is the bottleneck especially at the very low end it makes me wonder if one bit quantization of an extremely large model would be a gigabyte per gigabyte of ram better