Re:DeepScaleR: Surpassing O1-Preview with a 1.5B Model by Sc...
by simonw on Tuesday February 11, 2025 @04:17PM
(#43018494)
... well that's weird, I got exactly the same weird bug on the 7.1 GB F32 GGUF version: https://gist.github.com/simonw/58ff74a55b402dc55764a567b10ec...
Update: running the F16 model fixed that problem:
See https://news.ycombinator.com/item?id=43017599#43018767 and https://gist.github.com/simonw/9e79f96d69f10bc7ba540c87ea0e8...
[ Parent
| on HN ]
Re:DeepScaleR: Surpassing O1-Preview with a 1.5B Model by Sc...
by kristopolous on Tuesday February 11, 2025 @04:54PM
(#43018841)
makes me wonder if there's some exploitable data leak in a similar kind of formulation.