princeton-nlp/DataMUX

[NeurIPS 2022] DataMUX: Data Multiplexing for Neural Networks

39
/ 100
Emerging

This project helps machine learning engineers or researchers working with neural networks to efficiently train models by combining multiple data samples into a single input. It takes various text-based tasks, like sentence classification or named entity recognition, as input, and outputs trained models that perform these tasks with improved efficiency. The end-user is a machine learning practitioner looking to optimize neural network training.

No commits in the last 6 months.

Use this if you are a machine learning engineer or researcher looking to improve the efficiency of neural network training for natural language processing tasks.

Not ideal if you are not familiar with PyTorch or training neural networks, or if your primary focus is on non-NLP machine learning domains.

natural-language-processing machine-learning-engineering deep-learning-optimization text-classification named-entity-recognition
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

60

Forks

9

Language

Jupyter Notebook

License

Last pushed

Nov 24, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/princeton-nlp/DataMUX"

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