# Nokia Applied Research: anyjev

> A training-free layer that turns an open LLM into a decision model. It reads typed choice, yes/no and score answers from one prefill, removes option-order bias with no labels and, from a few hundred labels, calibrates or fits a closed-form head. Weights stay untouched.

- Page: https://systemonemodels.tech/nokia-applied-research/anyjev
- API: https://api.systemonemodels.tech/v1/models/nokia-applied-research/anyjev
- Download: `pip install systemonemodels && systemone pull nokia-applied-research/anyjev`

## Facts

| | |
|---|---|
| Maker | Nokia Applied Research (https://systemonemodels.tech/nokia-applied-research) |
| Decides | choice, score, noul, classify, route |
| Architecture | anyjev |
| Base model | qwen/qwen3-8b |
| Parameters | 8.0B |
| Licence | apache-2.0 |
| Availability | Open weights |
| Released | 2026-09-21 |
| Latest version | 0.1.0 |

## Reported evaluation

Suite: LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question. Numbers are the publisher's own.

- Decision accuracy: 77.1%
- Calibration error (ECE): 0.034

## Model card

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

# AnyJev

A training-free layer that turns an open LLM into a decision model. It reads typed choice, yes/no and score answers from one prefill, removes option-order bias with no labels and, from a few hundred labels, calibrates or fits a closed-form head. Weights stay untouched.

Every decision carries the level that produced it. L0 needs no labels and averages out option order (on Qwen3-8B, BANKING77 20-way, answer flips under reversed options fall from 0.230 to 0.073); L1 adds a temperature from 100 to 500 labels; L2 solves a closed-form head per question on a hidden state partway down, from 100 to 300 labels. This entry is AnyJev on Qwen3-8B: on LocalLLaMA/typed-decisions L2 scores 77.1% with a calibration error of 0.034 at block 24 of 36 (Jev's published figure: 72.7%). Heads for five Qwen3 models, 1.7B to 32B (73.0% to 79.9%), ship in the GitHub repository rather than on Hugging Face, and the Qwen weights come from Qwen, so there are no files to pull here. A head serves one question on one model, and the letter readout takes at most 26 options. Code and heads are Apache-2.0. By Jiamu Zhang, Tianze Yang and Liang Wu (Nokia) with Yucheng Shi (Tencent Hunyuan).

## 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 calibrated probability
- **classify** — assigns a category from a fixed taxonomy
- **route** — sends the input to one of several destinations

## At a glance

| | |
|---|---|
| Parameters | 8B |
| Base model | `qwen/qwen3-8b` |
| Maker | Nokia Applied Research |
| Released | 2026-09-21 |
| License | apache-2.0 |
| Reported accuracy | 77.1% |
| Reported latency | 33.9 ms per decision alone, 7.5 ms batched, on an H100 NVL (110-token state, block 24) |

## Read more

- [Source and results](https://github.com/nokia-applied-research/AnyJev)
- [Shipped heads (five Qwen3 models)](https://github.com/nokia-applied-research/AnyJev/tree/main/anyjev-heads)
- [anyjev on PyPI](https://pypi.org/project/anyjev/)

---

*This page was opened by System One for Nokia Applied Research, who can claim the organisation and take it over at any time.*

---

From System One Models — https://systemonemodels.tech/ · every System One model: https://systemonemodels.tech/system-one-models