Lugh@futurology.todayM to Futurology@futurology.todayEnglish · 16 days agoThis new Chinese AI Is outperforming ChatGPT — and its open-source & runs locallywww.tomsguide.comexternal-linkmessage-square16linkfedilinkarrow-up168arrow-down19
arrow-up159arrow-down1external-linkThis new Chinese AI Is outperforming ChatGPT — and its open-source & runs locallywww.tomsguide.comLugh@futurology.todayM to Futurology@futurology.todayEnglish · 16 days agomessage-square16linkfedilink
minus-squareFluffy Kitty Cat@slrpnk.netlinkfedilinkEnglisharrow-up3·15 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