Loading comparison…
HEAD TO HEAD
Ruoxi Qiu: canopy-jev and TextCortex: laya-cybersec, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | camellia86/canopy-jev | textcortex/laya-cybersec |
|---|---|---|
| Summary | Ruoxi Qiu's decision adapter for a frozen Qwen3.8-27B: a 6.3M-parameter LoRA on the last four text layers plus a numerical prior. One shared state feeds isolated question branches; each Choice, Noul or Score question returns probabilities with no generated tokens. | 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, noul, score | noul, classify |
| Architecture | canopy-jev | laya |
| Fine-tuned from | qwen/qwen3.8-27b | 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 | 87.4% | — |
| Calibration error | — | — |
| Valid action rate | — | — |
| Median latency | — | 95.4 ms |
| p95 latency | — | 149 ms |
| Evaluation suite | JevBench public set (231 items; 202 correct), the maker's own fresh zero-shot run with the upstream scorer | TextCortex saved run: 279 single-window inputs, PyTorch batch one |
| Latest version | 0.1.0 | 2026.10 |
| Variants | LICENSE, NOTICE, artifacts, licenses | encoder, onnx, tokenizer |
| Size of latest version | 24.1 MB | 1.8 GB |
| Files | 11 | 9 |
| Downloads | 0 | 0 |
| Stars | 0 | 0 |
| Tags | system-one, qwen, lora, adapter, shared-state, 27b | system-one, laya, encoder, prompt-injection, security, guardrails, multilingual, onnx, 322m |
| Updated | Oct 7, 2026 | Oct 7, 2026 |
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.
canopy-jev is from Ruoxi Qiu and laya-cybersec from TextCortex. Both have open weights you can download and run. Both answer noul questions. Only canopy-jev answers choice and score. Only laya-cybersec answers classify. laya-cybersec is the smaller model, at 322M parameters to 27B. canopy-jev is licensed apache-2.0; laya-cybersec, other.
Only canopy-jev publishes an accuracy figure (87.4% on JevBench public set (231 items; 202 correct), the maker's own fresh zero-shot run with the upstream scorer); laya-cybersec does not, so there is no comparison to make without your own test.
canopy-jev: Free (open weights). laya-cybersec: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull camellia86/canopy-jev and systemone pull textcortex/laya-cybersec download the weights.