hnrss.org

DeepScaleR: Surpassing O1-Preview with a 1.5B Model by Scaling RL

Article URL: https://pretty-radio-b75.notion.site/DeepScaleR-Surpassing-O1-Preview-with-a-1-5B-Model-by-Scaling-RL-19681902c1468005bed8ca303013a4e2 Comments URL: https://news.ycombinator.com/item?id=43017599 Points: 117 # Comments: 41

Fév 11, 2025 - 22:37
 0
DeepScaleR: Surpassing O1-Preview with a 1.5B Model by Scaling RL

Article URL: https://pretty-radio-b75.notion.site/DeepScaleR-Surpassing-O1-Preview-with-a-1-5B-Model-by-Scaling-RL-19681902c1468005bed8ca303013a4e2

Comments URL: https://news.ycombinator.com/item?id=43017599

Points: 117

# Comments: 41

Lire plus

Tags :

Article précédent

PassMark sees the first yearly drop in average CPU performance in its 20 years

Article suivant

Vigilance.fr - OpenStack Neutron : vulnérabilité via ML2/SR-IOV Port Disabling, ...

Articles similaires

The FFT Strikes Back: An Efficient Alternative to Self-Attention

The FFT Strikes Back: An Efficient Alternative to Self-...

Fév 26, 2025  0

Things you can do to clean up a fresh install of Windows 11 24H2 and Edge

Things you can do to clean up a fresh install of Window...

Fév 19, 2025  0

Your camera can take 3D photos. Your screen can display 3D photos.

Your camera can take 3D photos. Your screen can display...

Fév 26, 2025  0