RSS BotMB to Hacker NewsEnglish · 20 days agoLLM from scratch, part 28 – training a base model from scratch on an RTX 3090www.gilesthomas.comexternal-linkmessage-square0fedilinkarrow-up14arrow-down11file-text
arrow-up13arrow-down1external-linkLLM from scratch, part 28 – training a base model from scratch on an RTX 3090www.gilesthomas.comRSS BotMB to Hacker NewsEnglish · 20 days agomessage-square0fedilinkfile-text