dayyass/muse_tf2pt

Convert MUSE from TensorFlow to PyTorch and ONNX

21
/ 100
Experimental

This project allows developers to use a powerful multilingual sentence embedding model, MUSE, in PyTorch or ONNX formats. It takes the original TensorFlow model and converts it, providing a model that can process text in many languages to generate numerical representations (embeddings). Machine learning engineers and data scientists can use these embeddings for tasks like semantic search, text classification, or cross-lingual information retrieval.

No commits in the last 6 months.

Use this if you are a machine learning engineer or data scientist working with multilingual text and prefer to use PyTorch or ONNX for model inference or further fine-tuning.

Not ideal if you are exclusively working within a TensorFlow environment and do not need to integrate with PyTorch or ONNX ecosystems.

multilingual-NLP machine-learning-engineering sentence-embeddings text-analytics deep-learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

11

Forks

Language

Jupyter Notebook

License

MIT

Last pushed

May 22, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/dayyass/muse_tf2pt"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.