undefined | Better HN

0 pointsLeanderK2y ago0 comments

do you know if the LLM was fine-tuned in any way to the sparsity & quantisation? Or did it just work out of the box?

0 comments

I personally fine-tuned it with QAT = quantisation aware training and custom extensions to induce the sparsity.

j / k navigate · click thread line to collapse

0 pointsLeanderK2y ago0 comments

do you know if the LLM was fine-tuned in any way to the sparsity & quantisation? Or did it just work out of the box?

I personally fine-tuned it with QAT = quantisation aware training and custom extensions to induce the sparsity.

j / k navigate · click thread line to collapse