# agentmessier: messier-one

> A Qwen3.5-4B fine-tune that answers choice (up to 255 options), score and yes/no questions with a probability per option from one forward pass, read from label tokens in the language-model head, behind a TypeSafe-compatible /v1/systemone server. Non-commercial weights.

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

## Facts

| | |
|---|---|
| Maker | agentmessier (https://systemonemodels.ai/agentmessier) |
| Decides | choice, score, noul |
| Architecture | messier |
| Base model | qwen/qwen3.5-4b |
| Parameters | 5.3B |
| Licence | cc-by-nc-4.0 |
| Availability | Open weights |
| Released | 2026-10-06 |
| Latest version | 0.1.0 |

## Reported evaluation

Suite: JevBench public items (231; 197 correct), the maker's run with JevBench's runner and typesafe adapter. Numbers are the publisher's own.

- Decision accuracy: 85.3%

## Model card

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

# Messier One

A Qwen3.5-4B fine-tune that answers choice (up to 255 options), score and yes/no questions with a probability per option from one forward pass, read from label tokens in the language-model head, behind a TypeSafe-compatible /v1/systemone server. Non-commercial weights.

A rank-16 LoRA merged into Qwen3.5-4B. The trained readout sits in the head rows of 229 added option-label tokens, with one fitted temperature per question type; no overall calibration figure is published. On JevBench's 231 public items, in the maker's own run with JevBench's runner (not a leaderboard result), it answers 197. On its own many-option test, with reference answers from larger LLMs, it scores 97.6% at 2 to 26 options and 89.4% at 101 to 255. Option order can shift answers; arithmetic and date computation are unreliable. The weights are CC BY-NC 4.0: commercial use needs a licence from the maker, so they are not mirrored or packaged here. The serving code is Apache-2.0.

## 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 | 5.3B |
| Base model | `Qwen/Qwen3.5-4B` |
| Maker | agentmessier |
| Released | 2026-10-06 |
| License | cc-by-nc-4.0 |
| Reported accuracy | 85.3% |
| Reported latency | p50 46 ms easy, 51 ms standard, 95 ms hard per decision on one RTX 5090 (vLLM 0.30.0, BF16) |

## Get the weights

```bash
pip install systemonemodels
systemone pull agentmessier/messier-one
```

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

## Read more

- [Model card](https://huggingface.co/agentmessier/messier-one)
- [Serving code](https://github.com/agentmessier-ai/messier-one)

---

*This page was opened by System One for agentmessier, 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