# Muthukumaran Navaneethakrishnan: openjevx

> A Laya fine-tune by Muthukumaran Navaneethakrishnan for local, CPU-first yes/no, pick-one and rating questions over JSON or text. Ships as an 8-bit ONNX (598 MB) with a Go server that speaks /v1/systemone, plus the trainable checkpoint.

- Page: https://systemonemodels.ai/muthuishere/openjevx
- API: https://api.systemonemodels.ai/v1/models/muthuishere/openjevx
- Download: `pip install systemonemodels && systemone pull muthuishere/openjevx`

## Facts

| | |
|---|---|
| Maker | Muthukumaran Navaneethakrishnan (https://systemonemodels.ai/muthuishere) |
| Decides | choice, score, noul |
| Architecture | laya |
| Base model | convai-innovations/laya |
| Context | 512 tokens |
| Licence | apache-2.0 |
| Availability | Open weights |
| Released | 2026-09-28 |
| Latest version | 0.5.2 |

## Reported evaluation

Suite: The maker's held-out rule-checking gate (11,949 questions from his own generated set, no state shared with training). Numbers are the publisher's own.

- Decision accuracy: 98.9%

- Median latency: 85 ms

## Model card

<!-- generated by scripts/seed_catalog.py; edit content/models/catalog.yaml -->

# OpenJevX v0.5.2

A Laya fine-tune by Muthukumaran Navaneethakrishnan for local, CPU-first yes/no, pick-one and rating questions over JSON or text. Ships as an 8-bit ONNX (598 MB) with a Go server that speaks /v1/systemone, plus the trainable checkpoint.

Further trained from Laya on 791,889 decisions, mostly generated rule-checking, software-work and log-triage questions plus public labelled sets; no training data is published. The maker's own release gates score 98.5 to 100%, but his external sets are much lower: 68.6% on 102 public postmortems (20.6% confidently wrong) and 35.0% confidently wrong on operator logs. He says it is not a general reasoner. Calibration is a per-type temperature only; inputs are cut at 512 tokens. Runs in Docker, as native binaries or through a one-file Python port.

## What it decides

- **choice** — picks one option from a set
- **score** — places the input on an ordered scale
- **noul** — answers a yes/no question with one probability

## At a glance

| | |
|---|---|
| Base model | `convai-innovations/laya` |
| Maker | Muthukumaran Navaneethakrishnan |
| Released | 2026-09-28 |
| License | apache-2.0 |
| Reported accuracy | 98.9% |
| Reported latency | 85 ms p50 end to end for a typical 164-token request on an Apple M5 Pro CPU (ONNX Runtime) |

## Get the weights

```bash
pip install systemonemodels
systemone pull muthuishere/openjevx
```

The files are served from the maker's Hugging Face repository, [`muthuishere/openjevx`](https://huggingface.co/muthuishere/openjevx), and verified against the checksums recorded here.

## Read more

- [Model card](https://huggingface.co/muthuishere/openjevx)
- [Code, server and CLI](https://github.com/muthuishere/openjevx)

---

*This page was opened by System One for Muthukumaran Navaneethakrishnan, who can claim the organisation and take it over at any time.*

---

From System One Models — https://systemonemodels.ai/ · every System One model: https://systemonemodels.ai/system-one-models