amazon-science/llm-rank-pruning

LLM-Rank: A graph theoretical approach to structured pruning of large language models based on weighted Page Rank centrality as introduced by the related paper.

34
/ 100
Emerging

This tool helps AI researchers and machine learning engineers reduce the size and computational cost of large language models (LLMs) without significantly losing performance. It takes a pre-trained LLM and calibration data, then identifies and removes less important parts of the model. The output is a smaller, more efficient pruned LLM.

No commits in the last 6 months.

Use this if you need to deploy large language models on resource-constrained devices or reduce their operational cost while maintaining strong performance.

Not ideal if you are looking for a tool to train LLMs from scratch or fine-tune them on new data, as this focuses solely on post-training model compression.

large-language-models model-optimization AI-research machine-learning-engineering model-compression
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

8

Forks

3

Language

Python

License

Apache-2.0

Last pushed

Nov 29, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/amazon-science/llm-rank-pruning"

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