A family of open System One models by Mark Marosi that softmax option-letter logits at an answer slot: decider-0.8b, 2b, 4b and 35b-a3b on Qwen3.5 bases, decider-12b on Gemma-4-12B-it, and training-free readouts of larger chat models. This page carries decider-2b v11.
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, classify, route
noul, classify
Architecture
decider
laya
Fine-tuned from
qwen/qwen3.5-2b-base
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
75.2%
—
Calibration error
—
—
Valid action rate
—
—
Median latency
—
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 decider and laya-cybersec?
decider is from Mapika and laya-cybersec from TextCortex. Both have open weights you can download and run. Both answer noul and classify questions. Only decider answers choice, score and route. decider reads up to 32K tokens of state, against 1K tokens for laya-cybersec. laya-cybersec is the smaller model, at 322M parameters to 1.9B. decider is licensed apache-2.0; laya-cybersec, other.
Which is more accurate, decider or laya-cybersec?
Only decider publishes an accuracy figure (75.2% on Decider regression set, 28 held-out tasks (decider-2b v11)); laya-cybersec does not, so there is no comparison to make without your own test.
Which is cheaper, decider or laya-cybersec?
decider: Free (open weights). laya-cybersec: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run decider or laya-cybersec locally?
Yes, both: systemone pull mapika/decider and systemone pull textcortex/laya-cybersec download the weights.
