HUST-AI-HYZ/FARMS

Open source code for ICML 2025 Paper: Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias

24
/ 100
Experimental

FARMS helps machine learning practitioners fine-tune neural networks more effectively for tasks like image classification and large language model pruning. It takes an existing neural network model and, through a specialized training scheduler, improves its performance by adjusting learning rates based on an 'eigenspectrum analysis.' This is for machine learning researchers and engineers looking to optimize their model training workflows.

Use this if you are training or fine-tuning neural networks for image classification or large language models and want to improve model performance through advanced learning rate scheduling.

Not ideal if you are a beginner in machine learning or if your primary focus is not on deep learning model optimization and fine-tuning.

deep-learning-optimization image-classification llm-pruning neural-network-training scientific-machine-learning
No License No Package No Dependents
Maintenance 6 / 25
Adoption 8 / 25
Maturity 7 / 25
Community 3 / 25

How are scores calculated?

Stars

43

Forks

1

Language

Python

License

Last pushed

Nov 14, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/HUST-AI-HYZ/FARMS"

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