is there a kind of nanogpt for diffusion language models? i would love to unders... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		mynti 9 months ago \| parent \| context \| favorite \| on: Mercury: Ultra-fast language models based on diffu... is there a kind of nanogpt for diffusion language models? i would love to understand them better

nvtop 9 months ago [–]

This video has a live coding part which implements a masked diffusion generation process: https://www.youtube.com/watch?v=oot4O9wMohw

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact