An open Jev-style decision model by Andy Zhang: a LoRA adapter on Gemma 4 26B-A4B (also on Gemma 4 12B) that reads a state and returns a temperature-calibrated probability for every option of a yes/no, choice or score question in one forward pass.
Laya fine-tune that scans untrusted text (extracted files, knowledge-base documents, agent skills, tool descriptions) for prompt injection and data exfiltration in English and German, as a noul question answered in one forward pass. 322M parameters, PyTorch and ONNX.
Decides
choice, score, noul
noul, classify
Architecture
ajev
laya
Fine-tuned from
google/gemma-4-26b-a4b-it
convaiinnovations/laya-multilingual
License
apache-2.0
Unspecified; training data includes CC BY-NC-SA 4.0 material (non-commercial), not relicensed
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
—
Calibration error
—
—
Valid action rate
—
—
Median latency
49 ms
95.4 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 ajev and laya-cybersec?
ajev is from Andy Zhang and laya-cybersec from TextCortex. Both have open weights you can download and run. Both answer noul questions. Only ajev answers choice and score. Only laya-cybersec answers classify. laya-cybersec is the smaller model, at 322M parameters to 26B. ajev is licensed apache-2.0; laya-cybersec, other.
Which is more accurate, ajev or laya-cybersec?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, ajev or laya-cybersec?
ajev: Free (open weights). laya-cybersec: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, ajev or laya-cybersec?
By their publishers’ figures, ajev answers in about 49 ms at the median and laya-cybersec in about 95.4 ms — measured on different hardware, so treat it as a rough guide.
Can I run ajev or laya-cybersec locally?
Yes, both: systemone pull andy-zhang/ajev and systemone pull textcortex/laya-cybersec download the weights.
—
149 ms
Evaluation suite
Sequential requests, the maker's own measurement
TextCortex saved run: 279 single-window inputs, PyTorch batch one
