Isn't distillation done through SFT by having the student model approximate the ... | Hacker News

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

maleldil 42 days ago | parent | context | favorite | on: DeepSeek Harness developer preview

Isn't distillation done through SFT by having the student model approximate the teacher's output distribution?

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