HEAD TO HEAD
Convai Innovations: laya-noulxp-gpu and Kotoba Labs: open-jev-deberta-v3-large, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | convai-innovations/laya-noulxp-gpu | kotoba-labs/open-jev-deberta-v3-large |
|---|---|---|
| Summary | Unofficial NoulXP package of Convai Innovations' Laya (English) (Apache-2.0), fp16: checked against the model's own answers, none changed. Not made by Convai Innovations. | An independent Jev-shaped reproduction on DeBERTa-v3-large. One state and any number of choice, score and yes/no questions go in, and a calibrated distribution per question comes out of one forward pass. Public gold labels only. |
| Decides | choice, score, noul, classify, route | choice, score, noul, classify |
| Architecture | laya | open-jev |
| Fine-tuned from | convai-innovations/laya | microsoft/deberta-v3-large |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | — | 85.4% |
| Calibration error | — | 0.022 |
| Valid action rate | — | — |
| Median latency | — | 28 ms |
| p95 latency | — | — |
| Evaluation suite | — | Kotoba held-out test, seen question types (banking77, SST-5, BoolQ) |
| Latest version | 0.1.0 | 2026.09 |
| Variants | noulxp | — |
| Size of latest version | 958.6 MB | 1.6 GB |
| Files | 9 | 9 |
| Downloads | 75 | 2 |
| Stars | 0 | 0 |
| Tags | noulxp, unofficial, onnx, fp16, encoder, modernbert, rlcd | system-one, encoder, deberta, public-data, 434m |
| Updated | Nov 21, 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.
laya-noulxp-gpu is from Convai Innovations and open-jev-deberta-v3-large from Kotoba Labs. Both have open weights you can download and run. Both answer choice, score, noul and classify questions. Only laya-noulxp-gpu answers route. laya-noulxp-gpu is the smaller model, at 421M parameters to 434M.
Only open-jev-deberta-v3-large publishes an accuracy figure (85.4% on Kotoba held-out test, seen question types (banking77, SST-5, BoolQ)); laya-noulxp-gpu does not, so there is no comparison to make without your own test.
laya-noulxp-gpu: Free (open weights). open-jev-deberta-v3-large: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull convai-innovations/laya-noulxp-gpu and systemone pull kotoba-labs/open-jev-deberta-v3-large download the weights.