twinkle0331/LGTM
[ACL 2023] Code for paper “Tailoring Instructions to Student’s Learning Levels Boosts Knowledge Distillation”(https://arxiv.org/abs/2305.09651)
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.
Stars
38
Forks
3
Language
Python
License
Apache-2.0
Category
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.
Higher-rated alternatives
Guang000/Awesome-Dataset-Distillation
A curated list of awesome papers on dataset distillation and related applications.
dkozlov/awesome-knowledge-distillation
Awesome Knowledge Distillation
SforAiDl/KD_Lib
A Pytorch Knowledge Distillation library for benchmarking and extending works in the domains of...
SakurajimaMaiii/ProtoKD
[ICASSP 2023] Prototype Knowledge Distillation for Medical Segmentation with Missing Modality
HikariTJU/LD
Localization Distillation for Object Detection (CVPR 2022, TPAMI 2023)