---
license: cc-by-nc-4.0
base_model:
- facebook/nllb-200-1.3B
tags:
- translation
- dotnet
---

# NLLB Model 1.3B for Lopatnov.Translate

This repository contains an ONNX-converted version of the NLLB model, optimized for the [Lopatnov.Translate](https://github.com/lopatnov/translate) service. 
These files are converted from the original weights in the [facebook/nllb-200-1.3B](https://huggingface.co/facebook/nllb-200-1.3B) repository. 

## Conversion recipe

```bash
conda create -n model_export python=3.10 -y
conda activate model_export
pip install "optimum[onnxruntime,export,openvino]" transformers sentencepiece
optimum-cli export onnx --model facebook/nllb-200-1.3B --task seq2seq-lm --dtype fp32 --opset 18 ./model/nllb-200-1.3B-onnx
```

## Configuration

To configure model for the service, please modify `appsettings.json`:

### Example configuration:

```json
{
  "Models": {
    "nllb-200-1.3B": {
      "Type": "NLLB",
      "Path": "../../models/translate/nllb-200-1.3B",
      "EncoderFile": "encoder_model.onnx",
      "DecoderFile": "decoder_model.onnx",
      "TokenizerFile": "sentencepiece.bpe.model",
      "TokenizerConfigFile": "tokenizer.json",
      "MaxTokens": 512,
      "BeamSize": 1
    }
  },
  // These configurations are optional
  "Translation": {
    "AllowedModels": [ "nllb-200-1.3B" ], // Whitelist allowed models if needed
    "DefaultModel": "nllb-200-1.3B", // Set this model as the default
    "WarmUp": [ "nllb-200-1.3B" ] // Load the model into memory on startup
  }
}
```

*Note: Make sure the `Path` correctly points to the location of your downloaded `.onnx` files relative to application.*

## Documentation

For advanced configuration options, visit the [Official Documentation](https://github.com/lopatnov/translate/blob/main/docs/models.md#nllb-200-13b).