diff options
author | Pavol Rusnak <pavol@rusnak.io> | 2023-03-13 17:15:20 +0100 |
---|---|---|
committer | GitHub <noreply@github.com> | 2023-03-13 18:15:20 +0200 |
commit | d1f224712d78ab2cbb78777acfeb6739f660eb96 (patch) | |
tree | d08e2637149b43ce20aed276bef37575b179cf88 /quantize.sh | |
parent | 1808ee0500ea674b4bc2911acd0489ee5cbcef87 (diff) |
Add quantize script for batch quantization (#92)
* Add quantize script for batch quantization
* Indentation
* README for new quantize.sh
* Fix script name
* Fix file list on Mac OS
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Diffstat (limited to 'quantize.sh')
-rwxr-xr-x | quantize.sh | 15 |
1 files changed, 15 insertions, 0 deletions
diff --git a/quantize.sh b/quantize.sh new file mode 100755 index 00000000..6194649b --- /dev/null +++ b/quantize.sh @@ -0,0 +1,15 @@ +#!/usr/bin/env bash + +if ! [[ "$1" =~ ^[0-9]{1,2}B$ ]]; then + echo + echo "Usage: quantize.sh 7B|13B|30B|65B [--remove-f16]" + echo + exit 1 +fi + +for i in `ls models/$1/ggml-model-f16.bin*`; do + ./quantize "$i" "${i/f16/q4_0}" 2 + if [[ "$2" == "--remove-f16" ]]; then + rm "$i" + fi +done |