# Saechan Oh: malkuth

> Multilingual decision model with a Korean focus: a LoRA adapter and pointer head post-trained from Kev on frozen Qwen3.5-4B-Base, returning probabilities for choice, noul and score questions. Research-use-only weights.

- Page: https://systemonemodels.ai/saechan-oh/malkuth
- API: https://api.systemonemodels.ai/v1/models/saechan-oh/malkuth
- Download: `pip install systemonemodels && systemone pull saechan-oh/malkuth`

## Facts

| | |
|---|---|
| Maker | Saechan Oh (https://systemonemodels.ai/saechan-oh) |
| Decides | choice, score, noul, classify |
| Architecture | kev |
| Base model | qwen/qwen3.5-4b-base |
| Parameters | 4.0B |
| Context | 8K tokens |
| Licence | cc-by-nc-4.0 |
| Availability | Open weights |
| Released | 2026-09-24 |
| Latest version | 2026.09 |

## Reported evaluation

Suite: Malkuth evaluation, unweighted mean of 9 held-out suites not used in training (the maker's own). Numbers are the publisher's own.

- Decision accuracy: 72.4%
- Calibration error (ECE): 0.086

## Model card

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

# Malkuth-4B

Multilingual decision model with a Korean focus: a LoRA adapter and pointer head post-trained from Kev on frozen Qwen3.5-4B-Base, returning probabilities for choice, noul and score questions. Research-use-only weights.

A personal release by Saechan Oh. The repo holds the adapter only (33.8M trainable parameters plus head.pt, a pickle); the base downloads separately. Served with Kev's server, so a TypeSafe-style client works with a base URL change. Initialised from jaredpalmer/kev-4b; the published weights are an intermediate checkpoint chosen on the validation split. On the maker's own 29-suite evaluation, held-out accuracy (9 suites not trained on) is 0.724; 10 of the 29 suites, including 4 of 5 Korean ones, were in training, and the maker's figures show the probabilities are overconfident. The weights are research use only (XNLI and RACE in the training data); the code is Apache-2.0. Sibling Malkuth-2B.

## 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 | 4B |
| Base model | `qwen/qwen3.5-4b-base` |
| Maker | Saechan Oh |
| Released | 2026-09-24 |
| License | cc-by-nc-4.0 |
| Reported accuracy | 72.4% |

## Get the weights

```bash
pip install systemonemodels
systemone pull saechan-oh/malkuth
```

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

## Read more

- [Model card](https://huggingface.co/dhtocks/malkuth-4b)
- [Malkuth-2B](https://huggingface.co/dhtocks/malkuth-2b)
- [Code](https://github.com/newfull5/malkuth)

---

*This page was opened by System One for Saechan Oh, 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