An open family of System One models. A LoRA adapter plus a pointer head on a frozen Qwen base returns a distribution per typed question in one forward pass, serves TypeSafe's /v1/systemone contract, and ships a fitted temperature with every checkpoint.
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, score, noul, classify, route
choice, score, noul, classify
Architecture
kev
open-jev
Fine-tuned from
qwen/qwen3.5-4b-base
microsoft/deberta-v3-large
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
83.8%
85.4%
Calibration error
0.042
0.022
Valid action rate
—
—
Median latency
—
28 ms
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 kev and open-jev-deberta-v3-large?
kev is from Jared Palmer and open-jev-deberta-v3-large from Kotoba Labs. Both have open weights you can download and run. Both answer choice, score, noul and classify questions. Only kev answers route. kev reads up to 8K tokens of state, against 512 tokens for open-jev-deberta-v3-large. open-jev-deberta-v3-large is the smaller model, at 434M parameters to 4.0B.
Which is more accurate, kev or open-jev-deberta-v3-large?
They report on different suites — kev 83.8% on transfer-v4 (locked, out of domain), 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, kev or open-jev-deberta-v3-large?
kev: Free (open weights). open-jev-deberta-v3-large: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run kev or open-jev-deberta-v3-large locally?
Yes, both: systemone pull jared-palmer/kev and systemone pull kotoba-labs/open-jev-deberta-v3-large download the weights.
Evaluation suite
transfer-v4 (locked, out of domain)
Kotoba held-out test, seen question types (banking77, SST-5, BoolQ)
