I think the recurrence is a consequence of using a residual connection, seems li... | Hacker News

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

WithinReason 4 months ago | parent | context | favorite | on: Show HN: How I topped the HuggingFace open LLM lea...

I think the recurrence is a consequence of using a residual connection, seems like that makes the representation stay consistent across layers

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