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.
A family of open System One models by Mark Marosi that softmax option-letter logits at an answer slot: decider-0.8b, 2b, 4b and 35b-a3b on Qwen3.5 bases, decider-12b on Gemma-4-12B-it, and training-free readouts of larger chat models. This page carries decider-2b v11.
Decides
choice, noul, score
choice, score, noul, classify, route
Architecture
canopy-jev
decider
Fine-tuned from
qwen/qwen3.8-27b
qwen/qwen3.5-2b-base
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
87.4%
75.2%
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 canopy-jev and decider?
canopy-jev is from Ruoxi Qiu and decider from Mapika. Both have open weights you can download and run. Both answer choice, noul and score questions. Only decider answers classify and route. decider is the smaller model, at 1.9B parameters to 27B.
Which is more accurate, canopy-jev or decider?
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, decider 75.2% on Decider regression set, 28 held-out tasks (decider-2b v11) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, canopy-jev or decider?
canopy-jev: Free (open weights). decider: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run canopy-jev or decider locally?
Yes, both: systemone pull camellia86/canopy-jev and systemone pull mapika/decider download the weights.
—
Evaluation suite
JevBench public set (231 items; 202 correct), the maker's own fresh zero-shot run with the upstream scorer
