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 local, Jev-compatible decision model from Rizzo AI Academy. XHToken's Spark-X2.5-4B with a merged typed-decisions LoRA, run on llama.cpp; yes/no, choice and score questions share one prefill of the state and are read from the answer-letter logits. No text is generated.
Decides
noul, classify
choice, score, noul, classify, route
Architecture
laya
rizzo-flow
Fine-tuned from
convaiinnovations/laya-multilingual
xhtoken/spark-x2.5-4b
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
—
64.8%
Calibration error
—
0.112
Valid action rate
—
—
Median latency
95.4 ms
195 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 rizzo-flow?
laya-cybersec is from TextCortex and rizzo-flow from Rizzo AI Academy. Both have open weights you can download and run. Both answer noul and classify questions. Only rizzo-flow answers choice, score and route. laya-cybersec is the smaller model, at 322M parameters to 4.0B. laya-cybersec is licensed other; rizzo-flow, apache-2.0.
Which is more accurate, laya-cybersec or rizzo-flow?
Only rizzo-flow publishes an accuracy figure (64.8% on LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0); laya-cybersec does not, so there is no comparison to make without your own test.
Which is cheaper, laya-cybersec or rizzo-flow?
laya-cybersec: Free (open weights). rizzo-flow: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, laya-cybersec or rizzo-flow?
By their publishers’ figures, laya-cybersec answers in about 95.4 ms at the median and rizzo-flow in about 195 ms — measured on different hardware, so treat it as a rough guide.
Can I run laya-cybersec or rizzo-flow locally?
Yes, both: systemone pull textcortex/laya-cybersec and systemone pull rizzo-ai-academy/rizzo-flow download the weights.
149 ms
—
Evaluation suite
TextCortex saved run: 279 single-window inputs, PyTorch batch one
LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0
