A 144M-parameter System One model on the multilingual mmBERT-small encoder. Takes a state, a question and 2 to 20 options and returns one decision with probabilities for choice, score and yes/no questions, on a CPU.
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
julia
laya
Fine-tuned from
jhu-clsp/mmbert-small
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
73.2%
—
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 julia-1 and laya-cybersec?
julia-1 is from Supersonic Labs and laya-cybersec from TextCortex. Both have open weights you can download and run. Both answer noul and classify questions. Only julia-1 answers choice, score and route. julia-1 reads up to 8K tokens of state, against 1K tokens for laya-cybersec. julia-1 is the smaller model, at 144M parameters to 322M. julia-1 is licensed apache-2.0; laya-cybersec, other.
Which is more accurate, julia-1 or laya-cybersec?
Only julia-1 publishes an accuracy figure (73.2% on typed-decisions test set (400 cases, 2,000 questions)); laya-cybersec does not, so there is no comparison to make without your own test.
Which is cheaper, julia-1 or laya-cybersec?
julia-1: Free (open weights). laya-cybersec: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run julia-1 or laya-cybersec locally?
Yes, both: systemone pull supersonic-labs/julia-1 and systemone pull textcortex/laya-cybersec download the weights.
—
149 ms
Evaluation suite
typed-decisions test set (400 cases, 2,000 questions)
TextCortex saved run: 279 single-window inputs, PyTorch batch one
