News for hackers. Stuff that matters.

A comment on DeepSeek Harness. Parent comment

Re:DeepSeek Harness by maleldil on Friday August 14, 2026 @10:56PM (#49307162)
Isn't distillation done through SFT by having the student model approximate the teacher's output distribution?
[ Parent | on HN ]

There are no comments on this comment yet.