# Mathias Strasser: jeff

> A 0.8B fine-tune of Qwen3.5-0.8B that returns a calibrated probability for each listed option in one forward pass (choice, yes/no, score), through a trained readout head. v1.3 is adapter-first, with 15 per-task LoRA adapters; for zero-shot use the maker points to v1.2.

- Page: https://systemonemodels.ai/mathias-strasser/jeff
- API: https://api.systemonemodels.ai/v1/models/mathias-strasser/jeff
- Download: `pip install systemonemodels && systemone pull mathias-strasser/jeff`

## Facts

| | |
|---|---|
| Maker | Mathias Strasser (https://systemonemodels.ai/mathias-strasser) |
| Decides | choice, score, noul, classify, route |
| Architecture | jeff |
| Base model | qwen/qwen3.5-0.8b |
| Parameters | 800M |
| Licence | apache-2.0 |
| Availability | Open weights |
| Released | 2026-10-05 |
| Latest version | 1.3.0 |

## Reported evaluation

Suite: Jeff panel: 4,599 questions from BBH, Financial PhraseBank, JudgeBench, RAGTruth and WinoGrande (the maker's own sample). Numbers are the publisher's own.

- Decision accuracy: 78.6%
- Calibration error (ECE): 0.028
- Median latency: 26.6 ms

## Model card

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

# Jeff v1.3 (jeff-base)

A 0.8B fine-tune of Qwen3.5-0.8B that returns a calibrated probability for each listed option in one forward pass (choice, yes/no, score), through a trained readout head. v1.3 is adapter-first, with 15 per-task LoRA adapters; for zero-shot use the maker points to v1.2.

A personal project by Mathias Strasser, started from Denis Yarats' AutoJev recipe; not affiliated with TypeSafe and unrelated to other models named Jeff. English text only. Without an adapter the v1.3 base is weak on long, unfamiliar option lists (7.4% on legal clauses, against 66.0% for v1.2), so the zero-shot v1.2 builds (jeff-legacy/Jeff-Qwen3.5-0.8B and 2B) stay published. The adapters differ in licence: sanctions and soc are CC BY-NC 4.0 (never packaged here), and aml and trading-desk carry data-source terms of their own; Jeff-Gemma4-E2B follows the Gemma 4 terms. The training data mixes sources, some under CC BY-SA. Each adapter's held-out accuracy is on its own card (for example guard 98.2%, triage 91.5%). Python and TypeScript clients, GGUF builds and a jeff-serve server that switches adapters per request.

## 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
- **route** — sends the input to one of several destinations

## At a glance

| | |
|---|---|
| Parameters | 0.8B |
| Base model | `Qwen/Qwen3.5-0.8B` |
| Maker | Mathias Strasser |
| Released | 2026-10-05 |
| License | apache-2.0 |
| Reported accuracy | 78.6% |
| Reported latency | 26.6 ms median per decision, base alone, on an RTX PRO 6000 via jeff-serve (675 requests); 31.4 ms with one adapter |

## Get the weights

```bash
pip install systemonemodels
systemone pull mathias-strasser/jeff
```

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

## Read more

- [Model card](https://huggingface.co/mstrasser/jeff-base)
- [Code](https://github.com/firelex/jeff)
- [Docs and adapters](https://jeffhub.ai)
- [GGUF](https://huggingface.co/mstrasser/jeff-base-gguf)
- [Jeff-Qwen3.5-2B (v1.2, zero-shot)](https://huggingface.co/jeff-legacy/Jeff-Qwen3.5-2B)

---

*This page was opened by System One for Mathias Strasser, 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