How do you determine the importance of a layer in this case? | Hacker News

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

		Squeeze2664 6 months ago \| parent \| context \| favorite \| on: Qwen3-235B-A22B-Thinking-2507 How do you determine the importance of a layer in this case?

smallerize 6 months ago | [–]

https://unsloth.ai/blog/dynamic-v2

danielhanchen 6 months ago | | [–]

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 6 months ago | [–]

Afaik they have a test bench that they use and take the activation data from that.

danielhanchen 6 months ago | [–]

Yes we have around 1 to 3 million tokens of high quality self verified data that we use to calibrate models!

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