hppRC/simple-simcse-ja

Exploring Japanese SimCSE

24
/ 100
Experimental

This project offers pre-trained Japanese language models that can convert sentences into numerical representations, known as embeddings. These embeddings can then be used to find similar sentences for tasks like information retrieval or improving AI-generated text. It provides several fine-tuned models ready for use, catering to anyone working with Japanese text data who needs to understand semantic similarity.

No commits in the last 6 months.

Use this if you need to efficiently find Japanese sentences that are semantically similar to each other, for applications such as search, question answering, or enhancing generative AI with relevant information.

Not ideal if your primary need is for tasks other than semantic similarity, or if you are working exclusively with languages other than Japanese.

Japanese-language-processing semantic-search information-retrieval natural-language-understanding text-similarity
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 8 / 25

How are scores calculated?

Stars

69

Forks

4

Language

Python

License

Last pushed

Oct 31, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/hppRC/simple-simcse-ja"

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