sanyalsunny111/Early_Weight_Avg

[COLM 2024] Early Weight Averaging meets High Learning Rates for LLM Pre-training

19
/ 100
Experimental

This project helps machine learning engineers and researchers pre-train large language models (LLMs) more efficiently. It takes your training data and model configurations, then applies an 'Early Weight Averaging' technique to produce a better-performing LLM in less time. This is ideal for those focused on developing and optimizing LLMs.

No commits in the last 6 months.

Use this if you are pre-training large language models and want to accelerate convergence and improve generalization without incurring higher training costs.

Not ideal if you are working with already-trained models or smaller machine learning tasks outside of LLM pre-training.

LLM-pretraining model-optimization deep-learning natural-language-processing AI-research
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 5 / 25

How are scores calculated?

Stars

19

Forks

1

Language

Python

License

Last pushed

Oct 12, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/sanyalsunny111/Early_Weight_Avg"

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