Hacker News new | ask | show | jobs
by swyx 534 days ago
how about finetuning your 32B to be R1QWQKV?
1 comments
pico_creator 533 days ago
There is a current lack of "O1 style" reasoning dataset in open source space. QWQ did not release their dataset. So that would take some time for the community to prepare.

It's definitely something we are tracking to do as well =)

link