wait do sota models use mamba-like SSMs? this is the first im hearing this | Hacker News

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

dnautics 3 months ago | parent | context | favorite | on: Ask HN: Has anyone replaced Claude/GPT with a loca...

wait do sota models use mamba-like SSMs? this is the first im hearing this

nl 3 months ago [–]

Qwen 3.5 and above use Gated DeltaNet which alternate attention and SSM layers:

https://sebastianraschka.com/llms-from-scratch/ch04/08_delta...

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