A 2.8 MB byte-level transformer for GUI form filling. For each form element it returns one probability per typed option (fill an entity, check, click or skip), using jevlike's option-attention head.
An independent Jev-shaped reproduction on DeBERTa-v3-large. One state and any number of choice, score and yes/no questions go in, and a calibrated distribution per question comes out of one forward pass. Public gold labels only.
Decides
choice
choice, score, noul, classify
Architecture
cua-s1
open-jev
Fine-tuned from
—
microsoft/deberta-v3-large
License
mit
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
100.0%
85.4%
Calibration error
—
0.022
Valid action rate
—
—
Median latency
—
28 ms
p95 latency
—
—
Evaluation suite
Figures are from each model’s manifest; accuracy and latency are what the publishers report, on their own suites and hardware. Add a third model.
Questions
What is the difference between cua-s1-forms and open-jev-deberta-v3-large?
cua-s1-forms is from Cua and open-jev-deberta-v3-large from Kotoba Labs. Both have open weights you can download and run. Both answer choice questions. Only open-jev-deberta-v3-large answers score, noul and classify. cua-s1-forms is the smaller model, at 706K parameters to 434M. cua-s1-forms is licensed mit; open-jev-deberta-v3-large, apache-2.0.
Which is more accurate, cua-s1-forms or open-jev-deberta-v3-large?
They report on different suites — cua-s1-forms 100.0% on 196-decision evaluation on real forms, open-jev-deberta-v3-large 85.4% on Kotoba held-out test, seen question types (banking77, SST-5, BoolQ) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, cua-s1-forms or open-jev-deberta-v3-large?
cua-s1-forms: Free (open weights). open-jev-deberta-v3-large: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run cua-s1-forms or open-jev-deberta-v3-large locally?
Yes, both: systemone pull cua/cua-s1-forms and systemone pull kotoba-labs/open-jev-deberta-v3-large download the weights.
196-decision evaluation on real forms
Kotoba held-out test, seen question types (banking77, SST-5, BoolQ)
