microsoft/only_train_once

OTOv1-v3, NeurIPS, ICLR, TMLR, DNN Training, Compression, Structured Pruning, Erasing Operators, CNN, Diffusion, LLM

36
/ 100
Emerging

This project helps machine learning engineers and researchers train deep neural networks more efficiently. You provide your existing neural network model and data, and it automatically delivers a more compact, pruned model that performs just as well but is smaller and faster. This is ideal for those who need to deploy performant deep learning models to resource-constrained environments.

No commits in the last 6 months.

Use this if you need to reduce the size and computational cost of your deep learning models without sacrificing performance, especially when deploying to edge devices or platforms with limited resources.

Not ideal if your primary concern is exploring different model architectures from scratch or if you are not working with deep neural networks.

deep-learning-optimization model-compression edge-ai neural-network-deployment machine-learning-engineering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

50

Forks

6

Language

Python

License

MIT

Last pushed

Oct 10, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/microsoft/only_train_once"

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