mirror of
https://git.adityakumar.xyz/llama.cpp.git
synced 2024-11-14 00:59:43 +00:00
16 lines
309 B
Bash
16 lines
309 B
Bash
|
#!/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
|