yuanzhoulvpi2017/quick_sentence_transformers

sentence-transformers to onnx 让sbert模型推理效率更快

46
/ 100
Emerging

This project helps anyone using Sentence-BERT models for tasks like question-answering or semantic search who finds the process too slow. It takes an existing Sentence-BERT model and converts its core component into a more efficient format. The output is a faster model that still produces the same quality text embeddings. This is for machine learning practitioners deploying NLP models who need to improve inference speed.

166 stars. No commits in the last 6 months.

Use this if you are deploying Sentence-BERT models for applications requiring quick response times, such as real-time search or interactive chatbots.

Not ideal if you are only running Sentence-BERT models for offline, batch processing where latency is not a critical concern.

Natural Language Processing NLP Model Deployment Semantic Search Question Answering Systems AI Performance Optimization
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

166

Forks

32

Language

Python

License

MIT

Last pushed

Mar 11, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/yuanzhoulvpi2017/quick_sentence_transformers"

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