CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-29 08:41:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

Remove oboslete command from Docker script

Browse Source
This commit is contained in:
Georgi Gerganov
2023-03-23 22:39:44 +02:00
parent 0ba5a3a9a5
commit 4cc053b6d5
1 changed files with 1 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
.devops/tools.sh
View File

@@ -16,11 +16,7 @@ elif [[ $arg1 == '--quantize' || $arg1 == '-q' ]]; then
./quantize $arg2 ./quantize $arg2
elif [[ $arg1 == '--run' || $arg1 == '-r' ]]; then elif [[ $arg1 == '--run' || $arg1 == '-r' ]]; then
./main $arg2 ./main $arg2
elif [[ $arg1 == '--download' || $arg1 == '-d' ]]; then
python3 ./download-pth.py $arg2
elif [[ $arg1 == '--all-in-one' || $arg1 == '-a' ]]; then elif [[ $arg1 == '--all-in-one' || $arg1 == '-a' ]]; then
echo "Downloading model..."
python3 ./download-pth.py "$1" "$2"
echo "Converting PTH to GGML..." echo "Converting PTH to GGML..."
for i in `ls $1/$2/ggml-model-f16.bin*`; do for i in `ls $1/$2/ggml-model-f16.bin*`; do
if [ -f "${i/f16/q4_0}" ]; then if [ -f "${i/f16/q4_0}" ]; then
@@ -39,8 +35,6 @@ else
echo " ex: \"/models/7B/\" 1" echo " ex: \"/models/7B/\" 1"
echo " --quantize (-q): Optimize with quantization process ggml" echo " --quantize (-q): Optimize with quantization process ggml"
echo " ex: \"/models/7B/ggml-model-f16.bin\" \"/models/7B/ggml-model-q4_0.bin\" 2" echo " ex: \"/models/7B/ggml-model-f16.bin\" \"/models/7B/ggml-model-q4_0.bin\" 2"
echo " --download (-d): Download original llama model from CDN: https://agi.gpt4.org/llama/" echo " --all-in-one (-a): Execute --convert & --quantize"
echo " ex: \"/models/\" 7B"
echo " --all-in-one (-a): Execute --download, --convert & --quantize"
echo " ex: \"/models/\" 7B" echo " ex: \"/models/\" 7B"
fi fi