| language: | |
| - en | |
| license: apache-2.0 | |
| library_name: onnx | |
| tags: | |
| - onnx | |
| - translation | |
| - multilingual | |
| - forkjoin-ai | |
| base_model: facebook/nllb-200-distilled-1.3B | |
| pipeline_tag: translation | |
| # Nllb 200 Distilled 1.3B | |
| Forkjoin.ai conversion of [facebook/nllb-200-distilled-1.3B](https://huggingface.co/facebook/nllb-200-distilled-1.3B) to ONNX format for edge deployment. | |
| ## Model Details | |
| - **Source Model**: [facebook/nllb-200-distilled-1.3B](https://huggingface.co/facebook/nllb-200-distilled-1.3B) | |
| - **Format**: ONNX | |
| - **Converted by**: [Forkjoin.ai](https://forkjoin.ai) | |
| ## Usage | |
| ### With ONNX Runtime | |
| ```python | |
| import onnxruntime as ort | |
| session = ort.InferenceSession("nllb-200-distilled-1.3B-onnx.onnx") | |
| ``` | |
| ### With Transformers + Optimum | |
| ```python | |
| from optimum.onnxruntime import ORTModelForSequenceClassification | |
| model = ORTModelForSequenceClassification.from_pretrained("forkjoin-ai/nllb-200-distilled-1.3B-onnx") | |
| ``` | |
| ## About Forkjoin.ai | |
| [Forkjoin.ai](https://forkjoin.ai) runs AI models at the edge -- in-browser, on-device, zero cloud cost. These converted models power real-time inference, speech recognition, and natural language capabilities. | |
| All conversions are optimized for edge deployment within browser and mobile memory constraints. | |
| ## License | |
| Apache 2.0 (follows upstream model license) | |