ยท
AI & ML interests
Efficient Training Recipes of Large Models (mostly LLMs)
Organizations
replied to their post 10 months ago posted an update 10 months ago view post Are you familiar with reverse residual connections or looping in language models?Excited to share my Looped-GPT blog post and codebase ๐https://github.com/sanyalsunny111/Looped-GPTTL;DR: looping during pre-training improves generalization.Plot shows GPT2 LMs pre-trained with 15.73B OWT tokensP.S. This is my first post here โ I have ~4 followers and zero expectations for reach ๐