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.
Featherless AI's open server that turns a stock Hugging Face language model into a typed-decision endpoint. It reads the next-token logits for each question and builds the Choice, Score or Noul answer itself; no classifier head is trained and no JSON is generated.
Decides
choice
choice, score, noul, classify, route
Architecture
cua-s1
simple-jev
Fine-tuned from
—
google/gemma-4-26b-a4b-it
License
mit
apache-2.0
Availability
Open weights
Open weights + hosted API
Hosted by
—
Featherless AI
Input price
—
—
Decision accuracy
100.0%
—
Calibration error
—
—
Valid action rate
—
—
Median latency
—
—
p95 latency
—
—
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 simple-jev?
cua-s1-forms is from Cua and simple-jev from Featherless AI. cua-s1-forms has open weights you can download and run; simple-jev has open weights and a hosted API. Both answer choice questions. Only simple-jev answers score, noul, classify and route. cua-s1-forms is licensed mit; simple-jev, apache-2.0.
Which is more accurate, cua-s1-forms or simple-jev?
Only cua-s1-forms publishes an accuracy figure (100.0% on 196-decision evaluation on real forms); simple-jev does not, so there is no comparison to make without your own test.
Which is cheaper, cua-s1-forms or simple-jev?
cua-s1-forms: Free (open weights). simple-jev: Hosted, price not published, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Can I run cua-s1-forms or simple-jev locally?
Yes, both: systemone pull cua/cua-s1-forms and systemone pull featherless-ai/simple-jev download the weights.
