# Emre Vergili (Norovox): aubin

> Personal open-weights project: LoRA adapters on Gemma 4 (12B here; 31B and E4B siblings) that answer typed choice, yes/no and score questions by reading option-letter logits with a fitted temperature. Uncertain questions get a short written rationale and a re-score.

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

## Facts

| | |
|---|---|
| Maker | Emre Vergili (Norovox) (https://systemonemodels.ai/emrevrg) |
| Decides | choice, score, noul |
| Architecture | aubin |
| Base model | google/gemma-4-12b-it |
| Parameters | 12B |
| Licence | apache-2.0 |
| Availability | Open weights |
| Released | 2026-09-29 |
| Latest version | 2026.09 |

## Reported evaluation

Suite: Kev public suites (jaredpalmer/kev), transfer-v4 locked test, clean, 656 questions; the maker's own run, unquantised base, think-when-uncertain on. Numbers are the publisher's own.

- Decision accuracy: 87.8%
- Calibration error (ECE): 0.063

## Model card

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

# AUBIN-12B

Personal open-weights project: LoRA adapters on Gemma 4 (12B here; 31B and E4B siblings) that answer typed choice, yes/no and score questions by reading option-letter logits with a fitted temperature. Uncertain questions get a short written rationale and a re-score.

Jev-inspired. A rank-16 LoRA on google/gemma-4-12B-it with a fitted temperature; it needs the Gemma 4 base, and the repo holds the adapter and the maker's aubin package, which also serves a Laya/Jev-style endpoint. It scores option letters in one forward pass, but by default writes a short rationale and re-scores when the top two options are close (26 to 32% of questions, per the maker), so it is not purely one-pass unless that step is turned off. Siblings AUBIN-31B and AUBIN-E4B-v3. The family's web-agent, screenshot-click and grid-control adapters and the AUBIN-Omni router are not decision models and are not listed. On LocalLLaMA/typed-decisions the maker reports 72.9% for this adapter alone; the card's 77.55% headline fuses it with a separate classifier.

## 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 | 12B |
| Base model | `google/gemma-4-12B-it` |
| Maker | Emre Vergili (Norovox) |
| Released | 2026-09-29 |
| License | apache-2.0 |
| Reported accuracy | 87.8% |
| Reported latency | 486 ms per question on the fast path, 4-bit on one T4; about 6 to 7 s more on questions it thinks about |

## Get the weights

```bash
pip install systemonemodels
systemone pull emrevrg/aubin
```

The files are served from the maker's Hugging Face repository, [`emrevrg/AUBIN-12B`](https://huggingface.co/emrevrg/AUBIN-12B), and verified against the checksums recorded here.

## Read more

- [Model card](https://huggingface.co/emrevrg/AUBIN-12B)
- [Code](https://github.com/Emrevrg/aubin)
- [AUBIN-31B](https://huggingface.co/emrevrg/AUBIN-31B)

---

*This page was opened by System One for Emre Vergili (Norovox), 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