---
library_name: transformers.js
base_model: LtG/norbert3-base
tags:
- onnx
- transformers.js
- feature-extraction
- sentence-similarity
- norwegian
language:
- no
pipeline_tag: feature-extraction
license: apache-2.0
---

# ONNX version of LtG/norbert3-base

This repository contains **ONNX-converted weights** for the Norwegian language model [LtG/norbert3-base](https://huggingface.co/LtG/norbert3-base). 

The conversion enables this state-of-the-art Norwegian model to run directly in browsers or Node.js environments using [Transformers.js](https://huggingface.co/docs/transformers.js).

It includes both:
1.  **Quantized (int8):** Faster, smaller (default).
2.  **Full Precision (float32):** Higher theoretical accuracy.

## Usage (Node.js/Web)

First, install the library:
```bash
npm install @huggingface/transformers
````

### Option 1: Use Quantized Model (Recommended)
This is the default behavior. It loads model_quantized.onnx (approx. 4x smaller, faster inference).

```javascript
import { pipeline } from '@huggingface/transformers';

// Loads the model (automatically selects the quantized version)
const embedder = await pipeline(
  'feature-extraction',
  'lebchen/norbert3-base-onnx',
  { device: 'auto' }
);

const sentences = [
    "Dette er en setning på norsk.", 
    "Norbert er en språkmodell fra UiO."
];

// Norbert generally benefits from mean pooling for sentence representations
const output = await embedder(sentences, { pooling: 'mean', normalize: true });

console.log(output.tolist());
```

### Option 2: Use Full Precision Model
To load the uncompressed model.onnx, explicitly set quantized: false.

```javascript
const embedder = await pipeline(
  'feature-extraction',
  'lebchen/norbert3-base-onnx',
  { 
    device: 'auto', 
    quantized: false 
  }
);
```

## Credits & Attribution
The original model (NorBERT 3) was developed by the Language Technology Group (LTG) at the University of Oslo.

Original Repository: [LtG/norbert3-base](https://huggingface.co/ltg/norbert3-base)

Paper/Citation: Please refer to the [original model](https://huggingface.co/ltg/norbert3-base) card for proper citation if you use this in academic work.

This distribution is converted to ONNX for compatibility reasons and maintains the original Apache 2.0 license.