TsingmaoAI/MI-optimize

mi-optimize is a versatile tool designed for the quantization and evaluation of large language models (LLMs). The library's seamless integration of various quantization methods and evaluation techniques empowers users to customize their approaches according to specific requirements and constraints, providing a high level of flexibility.

38
/ 100
Emerging

This tool helps machine learning engineers and researchers optimize large language models (LLMs) for real-time applications and resource-constrained devices. You can take a large language model and compress it using various quantization techniques. The result is a smaller, more efficient model that maintains high performance and can be deployed in a wider range of scenarios.

No commits in the last 6 months.

Use this if you need to reduce the computational and memory demands of large language models while preserving their performance for deployment.

Not ideal if you are working with small models or do not require specialized compression techniques for deployment.

large-language-models model-optimization machine-learning-deployment model-quantization ML-inference
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

25

Forks

5

Language

Python

License

Last pushed

Nov 28, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/TsingmaoAI/MI-optimize"

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