# tokimoa: uratori-ja

> A Japanese decision model from tokimoa. Qwen3.5-4B with a merged LoRA and a scoring head read at a marker after each option returns calibrated yes/no, choice and score distributions in one forward pass, built for grounding checks, document comparison and RAG judgments.

- Page: https://systemonemodels.ai/tokimoa/uratori-ja
- API: https://api.systemonemodels.ai/v1/models/tokimoa/uratori-ja
- Download: `pip install systemonemodels && systemone pull tokimoa/uratori-ja`

## Facts

| | |
|---|---|
| Maker | tokimoa (https://systemonemodels.ai/tokimoa) |
| Decides | choice, score, noul, classify |
| Architecture | uratori |
| Base model | qwen/qwen3.5-4b |
| Parameters | 4.2B |
| Context | 2K tokens |
| Licence | apache-2.0 |
| Availability | Open weights |
| Released | 2026-10-06 |
| Latest version | 2026.09 |

## Reported evaluation

Suite: tokimoa/uratori-ja-eval test split (802 items; LLM-majority labels), the maker's own run. Numbers are the publisher's own.

- Decision accuracy: 86.7%
- Calibration error (ECE): 0.040

## Model card

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

# uratori-ja-4b

A Japanese decision model from tokimoa. Qwen3.5-4B with a merged LoRA and a scoring head read at a marker after each option returns calibrated yes/no, choice and score distributions in one forward pass, built for grounding checks, document comparison and RAG judgments.

Japanese only. Needs trust_remote_code and about 12 GB of GPU memory. The maker's evaluation labels are majority votes of a draft answer and three LLM judges, not human labels. Weaker on relative dates, numbers and long inputs; trained once, on a single seed. Siblings: uratori-ja-310m (CPU, ONNX), 2b and 9b (0.887 on the same test split), plus MLX builds. On the same items the maker's own run of Jev 1.13 scores 0.903.

## 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
- **classify** — assigns a category from a fixed taxonomy

## At a glance

| | |
|---|---|
| Parameters | 4.21B |
| Base model | `Qwen/Qwen3.5-4B` |
| Maker | tokimoa |
| Released | 2026-10-06 |
| License | apache-2.0 |
| Reported accuracy | 86.7% |
| Reported latency | about 100 ms per question on an RTX 5090 at batch 8 |

## Get the weights

```bash
pip install systemonemodels
systemone pull tokimoa/uratori-ja
```

The files are served from the maker's Hugging Face repository, [`tokimoa/uratori-ja-4b`](https://huggingface.co/tokimoa/uratori-ja-4b), and verified against the checksums recorded here.

## Read more

- [Model card](https://huggingface.co/tokimoa/uratori-ja-4b)
- [uratori-ja-9b](https://huggingface.co/tokimoa/uratori-ja-9b)
- [uratori-ja-310m (CPU)](https://huggingface.co/tokimoa/uratori-ja-310m)
- [Code](https://github.com/tokimoa/uratori)

---

*This page was opened by System One for tokimoa, 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