But you'd need to keep both models in parallel, right? Using M1 to keep computin... | Hacker News

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

santiagobasulto on May 22, 2023 | parent | context | favorite | on: PrivateGPT

But you'd need to keep both models in parallel, right? Using M1 to keep computing embeddings and using M2 for completions.

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