# Yuichi Tateno (hotchpotch): bekko-system-one

> Ultra-small English encoders (17M, 68M and 395M) fine-tuned from Ettin rerankers. Each answers choice, noul and score questions with a probability per candidate and no generated text. Experimental v0 by one developer; the weights have no licence assigned yet.

- Page: https://systemonemodels.ai/hotchpotch/bekko-system-one
- API: https://api.systemonemodels.ai/v1/models/hotchpotch/bekko-system-one
- Download: `pip install systemonemodels && systemone pull hotchpotch/bekko-system-one`

## Facts

| | |
|---|---|
| Maker | Yuichi Tateno (hotchpotch) (https://systemonemodels.ai/hotchpotch) |
| Decides | choice, noul, score |
| Architecture | bekko |
| Base model | cross-encoder/ettin-reranker-400m-v1 |
| Parameters | 395M |
| Licence | Unassigned: the weights licence is not finalised (treated as non-commercial); training code MIT |
| Availability | Open weights |
| Released | 2026-09-29 |
| Latest version | 2026.09 |

## Reported evaluation

Suite: The maker's short-input speed probe (4-option Choice, RTX 5090, 1 Oct 2026). Numbers are the publisher's own.

- Median latency: 5 ms
- p95 latency: 5.4 ms

## Model card

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

# Bekko System One v0

Ultra-small English encoders (17M, 68M and 395M) fine-tuned from Ettin rerankers. Each answers choice, noul and score questions with a probability per candidate and no generated text. Experimental v0 by one developer; the weights have no licence assigned yet.

Full fine-tunes of Ettin rerankers with a shared-prefix encoder: state and instructions are encoded once, every candidate attends to that prefix, and choice, noul and score heads give a softmax over the supplied candidates. English only; probabilities are not calibrated. The maker's own S1MB benchmark (a baseline-adjusted task average, not accuracy) gives 50.60 for the 400M against 59.59 for Jev 1.13; the maker says training shares 77 subset names with S1MB and that the models trail Jev on generalisation, hence "v0". The third-party Decision Index 0.3 puts the 400M at 15.24. Siblings bekko-system-one-v0-17m and -68m, with ONNX browser exports. No licence is assigned to the weights yet.

## What it decides

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

## At a glance

| | |
|---|---|
| Parameters | 395M |
| Base model | `cross-encoder/ettin-reranker-400m-v1` |
| Maker | Yuichi Tateno (hotchpotch) |
| Released | 2026-09-29 |
| License | Unassigned: the weights licence is not finalised (treated as non-commercial); training code MIT |
| Reported latency | 5.03 ms median per question on an RTX 5090 |

## Get the weights

```bash
pip install systemonemodels
systemone pull hotchpotch/bekko-system-one
```

The files are served from the maker's Hugging Face repository, [`hotchpotch/bekko-system-one-v0-400m`](https://huggingface.co/hotchpotch/bekko-system-one-v0-400m), and verified against the checksums recorded here.

## Read more

- [Model card](https://huggingface.co/hotchpotch/bekko-system-one-v0-400m)
- [bekko-system-one-v0-17m](https://huggingface.co/hotchpotch/bekko-system-one-v0-17m)
- [S1MB benchmark](https://github.com/hotchpotch/S1MB)

---

*This page was opened by System One for Yuichi Tateno (hotchpotch), 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