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

Prefix all example bins w/ llama-

Browse source
This commit is contained in:
Olivier Chafik 2024-06-08 13:42:01 +01:00
parent 23d0df5bd5
commit ab5efbb3b6
52 changed files with 288 additions and 254 deletions
Download patch file Download diff file Expand all files Collapse all files

6
.devops/tools.sh
View file

@ -10,11 +10,11 @@ shift
if [[ "$arg1" == '--convert' || "$arg1" == '-c' ]]; then
python3 ./convert-hf-to-gguf.py "$@"
elif [[ "$arg1" == '--quantize' || "$arg1" == '-q' ]]; then
./quantize "$@"
./llama-quantize "$@"
elif [[ "$arg1" == '--run' || "$arg1" == '-r' ]]; then
./llama "$@"
elif [[ "$arg1" == '--finetune' || "$arg1" == '-f' ]]; then
./finetune "$@"
./llama-finetune "$@"
elif [[ "$arg1" == '--all-in-one' || "$arg1" == '-a' ]]; then
echo "Converting PTH to GGML..."
for i in `ls $1/$2/ggml-model-f16.bin*`; do
@ -22,7 +22,7 @@ elif [[ "$arg1" == '--all-in-one' || "$arg1" == '-a' ]]; then
echo "Skip model quantization, it already exists: ${i/f16/q4_0}"
else
echo "Converting PTH to GGML: $i into ${i/f16/q4_0}..."
./quantize "$i" "${i/f16/q4_0}" q4_0
./llama-quantize "$i" "${i/f16/q4_0}" q4_0
fi
done
elif [[ "$arg1" == '--server' || "$arg1" == '-s' ]]; then