CASIA-LMC-Lab/FLAP

[AAAI 2024] Fluctuation-based Adaptive Structured Pruning for Large Language Models

44
/ 100
Emerging

This project helps machine learning engineers and researchers reduce the computational cost of deploying large language models (LLMs). It takes an existing LLM, such as LLaMA or Vicuna, and produces a smaller, more efficient version without needing extensive retraining. This makes LLMs faster and less resource-intensive to run, while maintaining strong performance on language tasks.

No commits in the last 6 months.

Use this if you need to deploy large language models more efficiently on devices with limited computational resources or when you want to reduce inference costs.

Not ideal if you need to prune a custom LLM architecture not based on the supported LLaMA or Vicuna families, or if you require full control over the fine-tuning process after pruning.

large-language-models model-compression natural-language-processing resource-optimization deep-learning-deployment
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

70

Forks

17

Language

Python

License

Apache-2.0

Last pushed

Jan 06, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/CASIA-LMC-Lab/FLAP"

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