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.
FrontiersMind's decision model on a base it pre-trained from scratch. Each question reads the state and its own tokens once and a 256-dimension pointer head scores the options; Choice and Score take up to 255 entries, and nothing is generated.
Decides
noul, classify
choice, score, noul
Architecture
laya
lumma-fev
Fine-tuned from
convaiinnovations/laya-multilingual
frontiersmind/lumma-0.6b-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
—
64.0%
Calibration error
—
—
Valid action rate
—
—
Median latency
95.4 ms
45.8 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 laya-cybersec and lumma-fev?
laya-cybersec is from TextCortex and lumma-fev from FrontiersMind. Both have open weights you can download and run. Both answer noul questions. Only laya-cybersec answers classify. Only lumma-fev answers choice and score. lumma-fev reads up to 8K tokens of state, against 1K tokens for laya-cybersec. laya-cybersec is the smaller model, at 322M parameters to 649M. laya-cybersec is licensed other; lumma-fev, apache-2.0.
Which is more accurate, laya-cybersec or lumma-fev?
Only lumma-fev publishes an accuracy figure (64.0% on typed-decisions (maker's table; split not stated)); laya-cybersec does not, so there is no comparison to make without your own test.
Which is cheaper, laya-cybersec or lumma-fev?
laya-cybersec: Free (open weights). lumma-fev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, laya-cybersec or lumma-fev?
By their publishers’ figures, lumma-fev answers in about 45.8 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 laya-cybersec or lumma-fev locally?
Yes, both: systemone pull textcortex/laya-cybersec and systemone pull frontiersmind/lumma-fev download the weights.
149 ms
—
Evaluation suite
TextCortex saved run: 279 single-window inputs, PyTorch batch one
