wangyuxinwhy/uniem

unified embedding model

43
/ 100
Emerging

This project helps you convert Chinese text into numerical representations called embeddings, which are crucial for many natural language processing tasks. It takes raw Chinese text as input and produces high-quality numerical vectors that capture the meaning of the text. This is designed for AI developers, researchers, or data scientists working with Chinese language applications.

876 stars. No commits in the last 6 months.

Use this if you need to generate high-quality, general-purpose embeddings for Chinese text, or if you want to fine-tune existing embedding models with your own data for specific Chinese language tasks.

Not ideal if you primarily work with non-Chinese languages or if you need a solution for tasks beyond text embedding, classification, or retrieval.

Chinese NLP text classification information retrieval semantic search natural language understanding
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

876

Forks

72

Language

Python

License

Apache-2.0

Last pushed

Sep 01, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/wangyuxinwhy/uniem"

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