# Maziyar Panahi: modernjev-decide

> A 149.6M ModernBERT-base cross-encoder with a scalar head that picks an agent's next action or tool from labels and descriptions you supply. Each option is scored against the state and a softmax ranks the set; no text is generated. Experimental preview, not calibrated.

- Page: https://systemonemodels.ai/maziyar-panahi/modernjev-decide
- API: https://api.systemonemodels.ai/v1/models/maziyar-panahi/modernjev-decide
- Download: `pip install systemonemodels && systemone pull maziyar-panahi/modernjev-decide`

## Facts

| | |
|---|---|
| Maker | Maziyar Panahi (https://systemonemodels.ai/maziyar-panahi) |
| Decides | choice, rank, route |
| Architecture | modernjev |
| Base model | answerdotai/modernbert-base |
| Parameters | 150M |
| Context | 4K tokens |
| Licence | apache-2.0 |
| Availability | Open weights |
| Released | 2026-09-30 |
| Latest version | 2026.09 |

## Reported evaluation

Suite: AgentToolDecisions-180K held-out test, next action type (1,158 decisions, 3 choices; the maker's split). Numbers are the publisher's own.

- Decision accuracy: 73.4%

## Model card

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

# ModernJEV-Decide-Preview

A 149.6M ModernBERT-base cross-encoder with a scalar head that picks an agent's next action or tool from labels and descriptions you supply. Each option is scored against the state and a softmax ranks the set; no text is generated. Experimental preview, not calibrated.

Choice and ranking only, no score or yes/no questions. Each option is scored as its own (state, option) pair, so a decision costs one pass per candidate. Probabilities are a softmax within the supplied set, not calibrated. Trained on 60,000 English agent decisions from the maker's AgentToolDecisions-180K (derived from NVIDIA's Nemotron-SFT-Agentic-v2). The maker reports 73.4% on next-action and 62.2% on tool selection (held-out), and 34.4% on unseen When2Call, below its majority reference, so transfer is not established. The maker calls it an experimental preview and "not a Jev reproduction"; label wording affects results.

## What it decides

- **choice** — picks one option from a set
- **rank** — orders a set of items
- **route** — sends the input to one of several destinations

## At a glance

| | |
|---|---|
| Parameters | 149.6M |
| Base model | `answerdotai/ModernBERT-base` |
| Maker | Maziyar Panahi |
| Released | 2026-09-30 |
| License | apache-2.0 |
| Reported accuracy | 73.4% |

## Get the weights

```bash
pip install systemonemodels
systemone pull maziyar-panahi/modernjev-decide
```

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

## Read more

- [Model card](https://huggingface.co/MaziyarPanahi/ModernJEV-Decide-Preview)
- [Training data](https://huggingface.co/datasets/MaziyarPanahi/AgentToolDecisions-180K)

---

*This page was opened by System One for Maziyar Panahi, 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