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.
A 149.6M ModernBERT-base cross-encoder with a scalar head that picks an agent's next action or tool from labels and descriptions you supply. Each option is scored against the state and a softmax ranks the set; no text is generated. Experimental preview, not calibrated.
Decides
noul, classify
choice, rank, route
Architecture
laya
modernjev
Fine-tuned from
convaiinnovations/laya-multilingual
answerdotai/modernbert-base
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
—
73.4%
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 modernjev-decide?
laya-cybersec is from TextCortex and modernjev-decide from Maziyar Panahi. Both have open weights you can download and run. Only laya-cybersec answers noul and classify. Only modernjev-decide answers choice, rank and route. modernjev-decide reads up to 4K tokens of state, against 1K tokens for laya-cybersec. modernjev-decide is the smaller model, at 150M parameters to 322M. laya-cybersec is licensed other; modernjev-decide, apache-2.0.
Which is more accurate, laya-cybersec or modernjev-decide?
Only modernjev-decide publishes an accuracy figure (73.4% on AgentToolDecisions-180K held-out test, next action type (1,158 decisions, 3 choices; the maker's split)); laya-cybersec does not, so there is no comparison to make without your own test.
Which is cheaper, laya-cybersec or modernjev-decide?
laya-cybersec: Free (open weights). modernjev-decide: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run laya-cybersec or modernjev-decide locally?
Yes, both: systemone pull textcortex/laya-cybersec and systemone pull maziyar-panahi/modernjev-decide download the weights.
p95 latency
149 ms
—
Evaluation suite
TextCortex saved run: 279 single-window inputs, PyTorch batch one
AgentToolDecisions-180K held-out test, next action type (1,158 decisions, 3 choices; the maker's split)
