# Doccy Health: solomon

> LoRA adapter and trained answer heads for Qwen3.8-27B. A document is read once into a reusable state; yes/no, single-choice, ordered-choice and multi-label questions then get probabilities read from letter logits, with optional ranked sentence pointers. No text is generated.

- Page: https://systemonemodels.ai/doccy-health/solomon
- API: https://api.systemonemodels.ai/v1/models/doccy-health/solomon
- Download: `pip install systemonemodels && systemone pull doccy-health/solomon`

## Facts

| | |
|---|---|
| Maker | Doccy Health (https://systemonemodels.ai/doccy-health) |
| Decides | choice, noul, classify |
| Architecture | solomon |
| Base model | qwen/qwen3.8-27b |
| Parameters | 27B |
| Licence | apache-2.0 |
| Availability | Open weights |
| Released | 2026-09-21 |
| Latest version | 1.1.0 |

## Reported evaluation

Suite: Doccy real-document test panel (802 questions over 54 public documents; AI-generated labels, not human-checked). Numbers are the publisher's own.

- Decision accuracy: 88.0%

## Model card

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

# Solomon v1.1

LoRA adapter and trained answer heads for Qwen3.8-27B. A document is read once into a reusable state; yes/no, single-choice, ordered-choice and multi-label questions then get probabilities read from letter logits, with optional ranked sentence pointers. No text is generated.

A general document-decision model; the card makes no clinical claims. Doccy's own panel is 802 questions over 54 public documents, with labels made by AI and never reviewed by a human. The v1.1 gain over v1.0 (+3.4 points) is not statistically established: the 95% document-bootstrap interval includes zero. Probabilities are served unscaled and miss the maker's own 0.03 ECE target for yes/no and ordered questions; answers stated at 5 to 20% come out yes more often than stated. The multi-label roll-up is a product of per-candidate probabilities, not a joint probability; the model never abstains; the evidence pointers are experimental. The base, Qwen3.8-27B at a pinned revision, is not included. The LoRA is applied only from the question onward, and a runtime binding refuses any engine other than the measured one; the MLX package in the repo is still v1.0. The maker disclosed three CC BY-SA documents among its 160 training documents. The third-party Decision Index (0.3 edition) lists it as "Solomon v1.1" with partial coverage.

## What it decides

- **choice** — picks one option from a set
- **noul** — answers a yes/no question with one probability
- **classify** — assigns a category from a fixed taxonomy

## At a glance

| | |
|---|---|
| Parameters | 27B |
| Base model | `Qwen/Qwen3.8-27B` |
| Maker | Doccy Health |
| Released | 2026-09-21 |
| License | apache-2.0 |
| Reported accuracy | 88.0% |

## Get the weights

```bash
pip install systemonemodels
systemone pull doccy-health/solomon
```

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

## Read more

- [Model card](https://huggingface.co/DoccyHealth/Solomon)
- [Base model](https://huggingface.co/Qwen/Qwen3.8-27B)

---

*This page was opened by System One for Doccy Health, 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