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 4B decision model fine-tuned from Qwen3.5-4B-Base. A state and typed questions (choice, yes/no, score) go in; a temperature-calibrated probability for every option comes out of one pass, through a self-hosted /v1/systemone-compatible server. Apache-2.0 weights and code.
Decides
choice, noul, score
choice, score, noul, classify, route
Architecture
canopy-jev
wald
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%
88.3%
Calibration error
—
0.045
Valid action rate
—
—
Median latency
—
33 ms
p95 latency
—
168 ms
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 canopy-jev and wald?
canopy-jev is from Ruoxi Qiu and wald from ORG2 AI. Both have open weights you can download and run. Both answer choice, noul and score questions. Only wald answers classify and route. wald is the smaller model, at 4.2B parameters to 27B.
Which is more accurate, canopy-jev or wald?
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, wald 88.3% on JevBench public set (231 items; 204 correct), maker's run with the JevBench CLI, v1.2, effort none; items used as a development scoreboard — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, canopy-jev or wald?
canopy-jev: Free (open weights). wald: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run canopy-jev or wald locally?
Yes, both: systemone pull camellia86/canopy-jev and systemone pull org2ai/wald download the weights.
JevBench public set (231 items; 202 correct), the maker's own fresh zero-shot run with the upstream scorer
JevBench public set (231 items; 204 correct), maker's run with the JevBench CLI, v1.2, effort none; items used as a development scoreboard
Latest version
0.1.0
1.2.0
Variants
LICENSE, NOTICE, artifacts, licenses
Dockerfile, LICENSE, NOTICE, model-files, reference, server
