jingtaozhan/JPQ
CIKM'21: JPQ substantially improves the efficiency of Dense Retrieval with 30x compression ratio, 10x CPU speedup and 2x GPU speedup.
This project helps information retrieval specialists and data scientists efficiently search very large text collections. It takes in search queries and a massive index of documents (like web pages or scientific papers) and quickly returns the most relevant results. The key benefit is a dramatic reduction in the size of the document index and faster search times, without losing accuracy.
No commits in the last 6 months.
Use this if you manage or build search systems for huge text datasets and need to significantly reduce storage costs and speed up query response times.
Not ideal if your dataset is small or if you require extremely high precision at the expense of any performance optimization.
Stars
52
Forks
11
Language
Python
License
MIT
Category
Last pushed
Feb 19, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jingtaozhan/JPQ"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
InterDigitalInc/CompressAI
A PyTorch library and evaluation platform for end-to-end compression research
quic/aimet
AIMET is a library that provides advanced quantization and compression techniques for trained...
tensorflow/compression
Data compression in TensorFlow
baler-collaboration/baler
Repository of Baler, a machine learning based data compression tool
thulab/DeepHash
An Open-Source Package for Deep Learning to Hash (DeepHash)