Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Tencent's 'Hunyuan-T1'–The First Mamba-Powered Ultra-Large Model. Parent comment
https://arxiv.org/abs/2501.19393
These tokens DO extend the thinking time. We are talking about causal autoregressive language models, and so these tokens can be used to guide the generation.
There are no comments on this comment yet.
https://arxiv.org/abs/2501.19393
These tokens DO extend the thinking time. We are talking about causal autoregressive language models, and so these tokens can be used to guide the generation.