twinkle0331/LGTM

[ACL 2023] Code for paper “Tailoring Instructions to Student’s Learning Levels Boosts Knowledge Distillation”(https://arxiv.org/abs/2305.09651)

31
/ 100
Emerging

This project offers an advanced technique for training smaller, more efficient natural language processing (NLP) models. It takes your existing NLP datasets and a larger, more powerful "teacher" model, then distills its knowledge into a smaller "student" model. This is ideal for machine learning engineers and researchers who need to deploy high-performing NLP models with reduced computational resources.

No commits in the last 6 months.

Use this if you need to create a smaller, faster NLP model that maintains high accuracy for text classification tasks, without sacrificing performance.

Not ideal if you are not working with text classification, or if you don't have existing larger models (teachers) from which to distill knowledge.

natural-language-processing machine-learning-engineering model-optimization text-classification model-deployment
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

38

Forks

3

Language

Python

License

Apache-2.0

Last pushed

Jun 04, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/twinkle0331/LGTM"

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