juyongjiang/KaSA

[ICLR'25] Code for KaSA, an official implementation of "KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models"

29
/ 100
Experimental

This project helps machine learning engineers and researchers efficiently adapt large language models (LLMs) to new, specific tasks without retraining the entire model. It takes an existing LLM and a dataset for a particular task (like classifying sentiment or understanding relationships between sentences) and outputs a finely tuned, task-specific LLM ready for use. It is designed for those who work with LLMs and need to specialize them for various applications.

No commits in the last 6 months.

Use this if you need to adapt powerful large language models to perform specific text understanding or generation tasks more accurately and efficiently with less computational cost.

Not ideal if you are looking for a ready-to-use application and do not have experience with machine learning model training and development environments.

large-language-models natural-language-processing model-adaptation text-classification fine-tuning
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 15 / 25

How are scores calculated?

Stars

20

Forks

5

Language

Jupyter Notebook

License

Last pushed

Jan 16, 2025

Commits (30d)

0

Get this data via API

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

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