HN
Hacker News
Top
New
Best
Ask
Show
Jobs
Comment by Squeeze2664 | Hacker News Reader
Parent
Full thread
Squeeze2664
·
How do you determine the importance of a layer in this case?
View on HN
smallerize
·
https://unsloth.ai/blog/dynamic-v2
danielhanchen
·
Yes also
https://unsloth.ai/blog/deepseekr1-dynamic
,
https://unsloth.ai/blog/dynamic-4bit
,
https://docs.unsloth.ai/basics/unsloth-dynamic-2.0-ggufs
kkzz99
·
Afaik they have a test bench that they use and take the activation data from that.
danielhanchen
·
Yes we have around 1 to 3 million tokens of high quality self verified data that we use to calibrate models!
Reply on news.ycombinator.com