# XY Space: yev

> A 4B System One decision model from XY Space: a LoRA on Qwen3.5-4B-Base, merged, that answers choice, yes/no (noul) and score questions about a state with a calibrated probability per option, read from the option-letter logits in one forward pass. Apache-2.0.

- Page: https://systemonemodels.ai/xy-space/yev
- API: https://api.systemonemodels.ai/v1/models/xy-space/yev
- Download: `pip install systemonemodels && systemone pull xy-space/yev`

## Facts

| | |
|---|---|
| Maker | XY Space (https://systemonemodels.ai/xy-space) |
| Decides | choice, score, noul |
| Architecture | yev |
| Base model | qwen/qwen3.5-4b-base |
| Parameters | 4.0B |
| Licence | apache-2.0 |
| Availability | Open weights |
| Released | 2026-10-04 |
| Latest version | 2026.09 |

## Reported evaluation

Suite: DecideBench v1.0 test, 400 items with worked examples (XY Space's own benchmark, choyiny/decidebench). Numbers are the publisher's own.

- Decision accuracy: 94.5%
- Calibration error (ECE): 0.060

## Model card

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

# yev0-4b

A 4B System One decision model from XY Space: a LoRA on Qwen3.5-4B-Base, merged, that answers choice, yes/no (noul) and score questions about a state with a calibrated probability per option, read from the option-letter logits in one forward pass. Apache-2.0.

Built by Cho Yin Yong of XY Space. The "Stage 0" model: one epoch of LoRA (rank 64) on 44k rows, merged at the root with the adapter alongside; the prompt format is Together's Tev1, used verbatim. Takes 2 to 6 options and reads letters A to F, with per-type temperatures. English only; accuracy drops beyond about 4k tokens; weak on date arithmetic and long multi-step workflows. XY Space's own runs elsewhere: JevBench public items 78.4% (a third-party board) and R-Judge at chance. DecideBench is XY Space's own benchmark. Synthetic labels were written and checked by Claude Opus 5.5, with no human review. Serving code (`yev serve`, /v1/systemone) is on GitHub; no hosted API.

## 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/Qwen3.5-4B-Base` |
| Maker | XY Space |
| Released | 2026-10-04 |
| License | apache-2.0 |
| Reported accuracy | 94.5% |

## Get the weights

```bash
pip install systemonemodels
systemone pull xy-space/yev
```

The files are served from the maker's Hugging Face repository, [`choyiny/yev0-4b`](https://huggingface.co/choyiny/yev0-4b), and verified against the checksums recorded here.

## Read more

- [Model card](https://huggingface.co/choyiny/yev0-4b)
- [Code](https://github.com/xyspacedev/yev)
- [DecideBench](https://huggingface.co/datasets/choyiny/decidebench)

---

*This page was opened by System One for XY Space, 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