mlx-examples icon indicating copy to clipboard operation
mlx-examples copied to clipboard

Published 20 hours ago • verified publisher icon ml-explore

add dequantize option to mlx_lm/convert.py

Open alwint3r opened this issue 11 months ago • 0 comments

This feature allows us to dequantize a 4-bit-quantized model.

alwint3r avatar Mar 08 '24 03:03 alwint3r