Robbert 2022 Dutch Sentence Transformers Onnx

🚀 LightEmbed/robbert-2022-dutch-sentence-transformers-onnx

This is an ONNX version of a sentence embedding model, optimized for speed and lightweight performance, aiming to provide efficient sentence similarity calculations.

🚀 Quick Start

This is the ONNX version of the Sentence Transformers model NetherlandsForensicInstitute/robbert-2022-dutch-sentence-transformers for sentence embedding, optimized for speed and lightweight performance. By utilizing onnxruntime and tokenizers instead of heavier libraries like sentence-transformers and transformers, this version ensures a smaller library size and faster execution. Below are the details of the model:

This ONNX model consists all components in the original sentence transformer model: Transformer, Pooling

📦 Installation

Using this model becomes easy when you have LightEmbed installed:

pip install -U light-embed

💻 Usage Examples

Basic Usage

Then you can use the model using the original model name like this:

from light_embed import TextEmbedding
sentences = [
    "This is an example sentence",
    "Each sentence is converted"
]

model = TextEmbedding('NetherlandsForensicInstitute/robbert-2022-dutch-sentence-transformers')
embeddings = model.encode(sentences)
print(embeddings)

Advanced Usage

Then you can use the model using onnx model name like this:

from light_embed import TextEmbedding
sentences = [
    "This is an example sentence",
    "Each sentence is converted"
]

model = TextEmbedding('LightEmbed/robbert-2022-dutch-sentence-transformers-onnx')
embeddings = model.encode(sentences)
print(embeddings)

📄 License

Citing & Authors

Binh Nguyen / binhcode25@gmail.com