vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update tools.sh

Browse source 
Update to use the correct file name "consolidated.*.pth". tools.sh is still looking for "ggml-model-f16.bin*` "  skipping the file convertions.
I wasn´t able to test this change  because for some reason when building the docker image in windows it can find the shell.
This commit is contained in:
RSereno 2023-03-22 20:29:20 +00:00 • committed by GitHub
parent ee8a788786
commit ae1519f681
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
.devops/tools.sh
View file

@ -22,7 +22,7 @@ elif [[ $arg1 == '--all-in-one' || $arg1 == '-a' ]]; then
echo "Downloading model..."
python3 ./download-pth.py "$1" "$2"
echo "Converting PTH to GGML..."
for i in `ls $1/$2/ggml-model-f16.bin*`; do
for i in `ls $1/$2/consolidated.*.pth`; do
if [ -f "${i/f16/q4_0}" ]; then
echo "Skip model quantization, it already exists: ${i/f16/q4_0}"
else