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.
TokenRhythm's prefill-only decision model for agent workflows. Built on its NeoHorse-1-4B (a Qwen3.5-4B derivative), it predicts Choice, Noul and Score answers over application-defined options without generating text, with optional single-image input.
Decides
noul, classify
choice, score, noul, classify, route
Architecture
laya
neohorse
Fine-tuned from
convaiinnovations/laya-multilingual
tokenrhythm/neohorse-1-4b
License
Unspecified; training data includes CC BY-NC-SA 4.0 material (non-commercial), not relicensed
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
75.3%
Calibration error
—
—
Valid action rate
—
—
Median latency
95.4 ms
—
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 laya-cybersec and neohorse-jev?
laya-cybersec is from TextCortex and neohorse-jev from TokenRhythm. Both have open weights you can download and run. Both answer noul and classify questions. Only neohorse-jev answers choice, score and route. laya-cybersec is the smaller model, at 322M parameters to 4.0B. laya-cybersec is licensed other; neohorse-jev, apache-2.0.
Which is more accurate, laya-cybersec or neohorse-jev?
Only neohorse-jev publishes an accuracy figure (75.3% on JevBench public set (231 items), vLLM, maker's run); laya-cybersec does not, so there is no comparison to make without your own test.
Which is cheaper, laya-cybersec or neohorse-jev?
laya-cybersec: Free (open weights). neohorse-jev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run laya-cybersec or neohorse-jev locally?
Yes, both: systemone pull textcortex/laya-cybersec and systemone pull tokenrhythm/neohorse-jev download the weights.
p95 latency
149 ms
—
Evaluation suite
TextCortex saved run: 279 single-window inputs, PyTorch batch one
JevBench public set (231 items), vLLM, maker's run
