Hacker News new | ask | show | jobs
by Alifatisk 473 days ago
Last time I tried QwQ or QvQ (a couple of days ago), their CoT was so long that it almost seemed endless, like it was stuck in a loop.

I hope this doesn't have the same issue.

2 comments

If that's an issue, there's a workaround using structure generation to force it to output a </thiking> token after some threshold and force it to write the final answer.

It's a method used to control thinking token generation showcased in this paper: https://arxiv.org/abs/2501.19393

it's not a bug it's a feature!