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 396M ModernBERT-large cross-encoder that answers typed questions about a text or a JSON state: one or several options, scores, yes/no with "not stated", spans with evidence quotes, rankings and numeric bins, each with a confidence and an act-or-escalate signal.
Decides
choice, noul, score
choice, score, noul, rank, extract
Architecture
canopy-jev
solvi
Fine-tuned from
qwen/qwen3.8-27b
answerdotai/modernbert-large
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
87.4%
59.4%
Calibration error
—
0.210
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 solvi?
canopy-jev is from Ruoxi Qiu and solvi from solvi. Both have open weights you can download and run. Both answer choice, noul and score questions. Only solvi answers rank and extract. solvi is the smaller model, at 396M parameters to 27B.
Which is more accurate, canopy-jev or solvi?
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, solvi 59.4% on Fast Decisions public dev split (100 rows x 17 domains, macro), the maker's own harness, zero-shot — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, canopy-jev or solvi?
canopy-jev: Free (open weights). solvi: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run canopy-jev or solvi locally?
Yes, both: systemone pull camellia86/canopy-jev and systemone pull solvi-ai/solvi download the weights.
Evaluation suite
JevBench public set (231 items; 202 correct), the maker's own fresh zero-shot run with the upstream scorer
Fast Decisions public dev split (100 rows x 17 domains, macro), the maker's own harness, zero-shot
