mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-10-31 08:51:55 +00:00
d1f224712d
* 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>
16 lines
309 B
Bash
Executable File
16 lines
309 B
Bash
Executable File
#!/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
|