# TriusAI: kapteeni

> Kapteeni, by Zetian Lin (TriusAI): a LoRA-tuned Qwen3-4B with small readout heads that serves the Jev System One wire format. Each question, option or score level gets its own pass; answers are probabilities, never generated text. Weights CC BY-SA 4.0.

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

## Facts

| | |
|---|---|
| Maker | TriusAI (https://systemonemodels.ai/triusai) |
| Decides | choice, score, noul |
| Architecture | kapteeni |
| Base model | qwen/qwen3-4b-instruct-2507 |
| Parameters | 4.0B |
| Licence | cc-by-sa-4.0 |
| Availability | Open weights |
| Released | 2026-09-25 |
| Latest version | 2026.09 |

## Reported evaluation

Suite: JevBench v1.4 public half (231 items), the maker's own run with the benchmark's code; not an official rank. Numbers are the publisher's own.

- Decision accuracy: 71.0%
- Calibration error (ECE): 0.050

## Model card

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

# Kapteeni v1 (meticulous)

Kapteeni, by Zetian Lin (TriusAI): a LoRA-tuned Qwen3-4B with small readout heads that serves the Jev System One wire format. Each question, option or score level gets its own pass; answers are probabilities, never generated text. Weights CC BY-SA 4.0.

Built by one person, Zetian Lin, under the TriusAI label. Small MLP readout heads sit on the last token's hidden state, with temperature scaling per question type. Siblings: kapteeni-v1-intuit (more accurate on well-formed numeric, temporal and multi-step traffic, less well calibrated) and kapteeni-v1.1c (2 October, on Qwen3.5-4B, one attached image, English and Chinese). On the third-party JevBench v1.4 public half, the maker's own runs give 0.710, 0.714 and 0.766 for the three, which the maker says are not an official rank. English-first; weak on long policies, multi-hop and temporal or numeric questions. The weights are CC BY-SA 4.0 because of share-alike training data (MultiNLI, FEVER); the code is Apache-2.0.

## 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

| | |
|---|---|
| Parameters | 4B |
| Base model | `Qwen/Qwen3-4B-Instruct-2507` |
| Maker | TriusAI |
| Released | 2026-09-25 |
| License | cc-by-sa-4.0 |
| Reported accuracy | 71.0% |

## Get the weights

```bash
pip install systemonemodels
systemone pull triusai/kapteeni
```

The files are served from the maker's Hugging Face repository, [`TriusAI/kapteeni-v1-meticulous`](https://huggingface.co/TriusAI/kapteeni-v1-meticulous), and verified against the checksums recorded here.

## Read more

- [Model card](https://huggingface.co/TriusAI/kapteeni-v1-meticulous)
- [kapteeni-v1.1c (multimodal)](https://huggingface.co/TriusAI/kapteeni-v1.1c)
- [Code](https://github.com/TriusAI/Kapteeni)

---

*This page was opened by System One for TriusAI, 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