▌system-one

~ / models / open-weights / cua-s1

Cua-S1

Research stack for small specialist computer-use models. First checkpoint is form-oriented: cua-s1-forms, a 706K-param option scorer with its training dataset on Hugging Face. Planning and execution stay separate.

section
Models
group
Open weights
source
github.com
added to list
sep 20

No history yet: this chart appears once there are a few daily snapshots.

also in Open weights