Ruoxi Qiu's decision adapter for a frozen Qwen3.8-27B: a 6.3M-parameter LoRA on the last four text layers plus a numerical prior. One shared state feeds isolated question branches; each Choice, Noul or Score question returns probabilities with no generated tokens.
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.
Decides
choice, noul, score
choice, score, noul, classify, route
Architecture
canopy-jev
kev
Fine-tuned from
qwen/qwen3.8-27b
qwen/qwen3.5-4b-base
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
87.4%
83.8%
Calibration error
—
0.042
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 canopy-jev and kev?
canopy-jev is from Ruoxi Qiu and kev from Jared Palmer. Both have open weights you can download and run. Both answer choice, noul and score questions. Only kev answers classify and route. kev is the smaller model, at 4.0B parameters to 27B.
Which is more accurate, canopy-jev or kev?
They report on different suites — canopy-jev 87.4% on JevBench public set (231 items; 202 correct), the maker's own fresh zero-shot run with the upstream scorer, kev 83.8% on transfer-v4 (locked, out of domain) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, canopy-jev or kev?
canopy-jev: Free (open weights). kev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run canopy-jev or kev locally?
Yes, both: systemone pull camellia86/canopy-jev and systemone pull jared-palmer/kev download the weights.
Evaluation suite
JevBench public set (231 items; 202 correct), the maker's own fresh zero-shot run with the upstream scorer
