amazon-science/mezo_svrg

Code the ICML 2024 paper: "Variance-reduced Zeroth-Order Methods for Fine-Tuning Language Models"

21
/ 100
Experimental

This helps AI/ML researchers and practitioners fine-tune large language models (LLMs) more efficiently. It takes a pre-trained Hugging Face LLM and a GLUE benchmark dataset, then applies advanced optimization algorithms to improve the model's performance on specific tasks. Researchers focused on deep learning optimization or natural language processing would use this.

No commits in the last 6 months.

Use this if you are an AI/ML researcher or practitioner looking to fine-tune large language models with state-of-the-art, memory-efficient, variance-reduced optimization methods to achieve better performance on NLP benchmarks.

Not ideal if you are looking for a no-code solution or a tool for general-purpose NLP tasks beyond LLM fine-tuning and optimization research.

AI/ML Research Natural Language Processing Large Language Models Model Fine-tuning Deep Learning Optimization
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

12

Forks

Language

Python

License

Apache-2.0

Last pushed

Jun 25, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/amazon-science/mezo_svrg"

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