luyug/GC-DPR
Train Dense Passage Retriever (DPR) with a single GPU
This project helps machine learning engineers or researchers train a Dense Passage Retriever (DPR) model more efficiently. It takes question-answer datasets and passage collections to produce a trained retriever capable of finding relevant passages for open-domain questions. This is specifically designed for those working with limited GPU memory who need to train state-of-the-art information retrieval systems.
136 stars. No commits in the last 6 months.
Use this if you need to train a high-quality Dense Passage Retriever model for open-domain question answering, but are constrained by the memory of a single or limited number of GPUs.
Not ideal if you have ample high-memory GPU resources or are not working with dense passage retrieval models.
Stars
136
Forks
21
Language
Python
License
—
Category
Last pushed
Jun 16, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/luyug/GC-DPR"
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)