---
title: OneJev1.5g-31B
canonical_url: "https://www.modelscope.ai/models/OmniJev/OneJev1.5g-31B"
md_url: "https://www.modelscope.ai/models/OmniJev/OneJev1.5g-31B.md"
repository: OmniJev/OneJev1.5g-31B
last_updated: 2026-11-11
license: apache-2.0
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - gemma4
architectures:
  - Gemma4ForConditionalGeneration
base_model:
  - google/gemma-4-31B-it
base_model_relation: finetune
parameters: 31.3B
tensor_type:
  - BF16
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 13
stars: 0
tags:
  - onejev
  - system-one
  - decision-model
  - calibration
  - multimodal
  - gui-agent
---

# OneJev1.5g-31B

> OneJev1.5g-31B - An open-source model by OmniJev on ModelScope. OneJev1.5g-31B is a multimodal System One decision model built on google/gemma-4-31B-it. Give it a screenshot, a photo or plain text along with a few typed questions, and it returns a calibrated…

OmniJev/OneJev1.5g-31B is a 31.3B-parameter image-text-to-text model on ModelScope. licensed under apache-2.0. derived from google/gemma-4-31B-it.

- **Repository**: OmniJev/OneJev1.5g-31B
- **License**: apache-2.0
- **Tasks**: image-text-to-text
- **Parameters**: 31.3B
- **Base model**: google/gemma-4-31B-it
- **Tags**: onejev, system-one, decision-model, calibration, multimodal, gui-agent
- **Downloads**: 13
- **Stars**: 0
- **Last updated**: 2026-11-11

Source: https://www.modelscope.ai/models/OmniJev/OneJev1.5g-31B

---

<p align="center">
  <picture>
    <source media="(prefers-color-scheme: dark)" srcset="assets/banner-dark.svg">
    <img alt="OneJev1.5g-31B, a Multimodal System One Decision Model" src="assets/banner.svg" width="100%">
  </picture>
</p>

<p align="center">
  <a href="https://huggingface.co/OmniJev"><img alt="Hugging Face" src="https://img.shields.io/badge/Hugging_Face-OmniJev-FFD21E?style=flat-square&logo=huggingface&logoColor=black"></a>
  <a href="https://github.com/OmniJev/OneJev"><img alt="GitHub" src="https://img.shields.io/badge/GitHub-OmniJev%2FOneJev-181717?style=flat-square&logo=github&logoColor=white"></a>
  <a href="https://omnijev.github.io/OneJev/"><img alt="Website" src="https://img.shields.io/badge/Website-OneJev-0A84FF?style=flat-square&logo=googlechrome&logoColor=white"></a>
  <a href="https://github.com/OmniJev/OneJev/blob/main/LICENSE"><img alt="License" src="https://img.shields.io/badge/License-Apache_2.0-D22128?style=flat-square&logo=apache&logoColor=white"></a>
</p>

OneJev1.5g-31B is a multimodal System One decision model built on [google/gemma-4-31B-it](https://huggingface.co/google/gemma-4-31B-it). Give it a screenshot, a photo or plain text along with a few typed questions, and it returns a calibrated probability for every option in a single forward pass.

## Quick start

```bash
uv venv -p 3.12 && source .venv/bin/activate
uv pip install flide torchvision
flide serve --model OmniJev/OneJev1.5g-31B
```

In another terminal, run this example with your own `screenshot.png`:

```bash
IMG=$(base64 -w0 screenshot.png)
curl http://localhost:8000/v1/systemone -H "Content-Type: application/json" -d @- <<EOF
{
  "state": {"task": "Pay the open invoice from ACME", "screen": "<image:1>"},
  "media": [{"type": "image", "data": "data:image/png;base64,$IMG"}],
  "questions": {
    "done": {"type": "noul", "instructions": "The invoice has been paid"},
    "next": {"type": "choice", "instructions": "What should the agent do next?",
             "criteria": {"click": "click an element", "type": "type text", "scroll": "scroll", "stop": "stop"}},
    "progress": {"type": "score", "instructions": "How far along is the task?",
                 "criteria": ["not started", "halfway", "almost done", "done"]}
  }
}
EOF
```

`answers.done.noul` is the probability of yes, `answers.next.probabilities` gives one probability per option and `answers.progress.score` is the expected level.

[Flide](https://github.com/OmniJev/Flide) ([paper](https://arxiv.org/abs/2610.42148)) serves TypeSafe's System One API plus a `media` field for images. More examples are on [GitHub](https://github.com/OmniJev/OneJev).