search

huggingface / optimum-quanto

A pytorch quantization backend for optimum
Apache License 2.0
645 stars 36 forks source link

1.58 bit quantization #176

Closed leo-gan closed 1 month ago

leo-gan commented 2 months ago

Any news on the implementation of the [-1, 0, 1] quantization based on the The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits article?

github-actions[bot] commented 1 month ago

This issue is stale because it has been open 30 days with no activity. Remove stale label or comment or this will be closed in 5 days.