# Berget AI: bev

> Berget AI's System One model for gating agent commands: a LoRA adapter and a fine-tuned joint schema head on Cloudflare's Clef-Flash that answer noul, choice and score questions over a state in one forward pass. Trained on Swedish and English operations decisions.

- Page: https://systemonemodels.ai/berget-ai/bev
- API: https://api.systemonemodels.ai/v1/models/berget-ai/bev
- Download: `pip install systemonemodels && systemone pull berget-ai/bev`

## Facts

| | |
|---|---|
| Maker | Berget AI (https://systemonemodels.ai/berget-ai) |
| Decides | noul, choice, score |
| Architecture | clef |
| Base model | cloudflare/clef-flash |
| Parameters | 9.0B |
| Licence | apache-2.0 |
| Availability | Open weights |
| Released | 2026-10-04 |
| Latest version | 2026.09 |

## Reported evaluation

Suite: Berget held-out risk split (16,902 questions; same operations-traffic corpora as training). Numbers are the publisher's own.

- Decision accuracy: 97.0%

## Model card

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

# bev-1

Berget AI's System One model for gating agent commands: a LoRA adapter and a fine-tuned joint schema head on Cloudflare's Clef-Flash that answer noul, choice and score questions over a state in one forward pass. Trained on Swedish and English operations decisions.

A rank-16 LoRA (about 116 MB) on Cloudflare's Clef-Flash plus a replacement joint head; it needs the base weights and Cloudflare's joint_schema_model.py. Trained on 221,759 judged operations decisions (risk and privacy, memory, routing, evasion), with labels checked by a larger model and human review. Berget's own held-out results come from the training corpora: risk 97.0% (base 93.5%), evasion 93.3% on 90 cases, red team 74% on 34 commands, and 82.8% on a general Jev-style set of 1,200 (base 80.6%); no calibration claim. It is the model behind Berget's MIT-licensed guardrails-md gate for coding agents.

## What it decides

- **noul** — answers a yes/no question with one probability
- **choice** — picks one option from a set
- **score** — places the input on an ordered scale

## At a glance

| | |
|---|---|
| Parameters | 9B |
| Base model | `Cloudflare/clef-flash` |
| Maker | Berget AI |
| Released | 2026-10-04 |
| License | apache-2.0 |
| Reported accuracy | 97.0% |

## Get the weights

```bash
pip install systemonemodels
systemone pull berget-ai/bev
```

The files are served from the maker's Hugging Face repository, [`bergetai/bev-1`](https://huggingface.co/bergetai/bev-1), and verified against the checksums recorded here.

## Read more

- [Model card](https://huggingface.co/bergetai/bev-1)
- [guardrails-md gate](https://github.com/berget-ai/guardrails-md)
- [Base model (Clef-Flash)](https://huggingface.co/Cloudflare/clef-flash)

---

*This page was opened by System One for Berget AI, 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