Re:DeepThought-8B: A small, capable reasoning model
by andai on Saturday November 30, 2024 @01:38PM
(#42283194)
Thanks. If I'm reading this right, the limiting factor on the intelligence of current LLMs is not the network size, nor training data (size/quality) but rather the architecture? Do we know of a better one for complex computations / "reasoning"?
[ Parent
| on HN ]
There are no comments on this comment yet.