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 US stops sharing air quality data from embassies worldwide

The US stops sharing air quality data from embassies wo...

Mar 6, 2025  0

DigiKey's Tariff Resources

Fév 22, 2025  0

Sweden Investigates New Cable Break Under Baltic Sea

Sweden Investigates New Cable Break Under Baltic Sea

Fév 21, 2025  0