tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-18 05:56:00 -04:00
Code Issues Packages Projects Releases Wiki Activity

Docker: change to calling convert.py (#1641)

Browse Source 
Deprecation disclaimer was added to convert-pth-to-ggml.py
This commit is contained in:
Jiří Podivín
2023-06-03 14:11:53 +02:00
committed by GitHub
parent 136476e898
commit b5c85468a3
2 changed files with 5 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
.devops/tools.sh
View File

@@ -11,7 +11,7 @@ shift
arg2="$@"
if [[ $arg1 == '--convert' || $arg1 == '-c' ]]; then
python3 ./convert-pth-to-ggml.py $arg2
python3 ./convert.py $arg2
elif [[ $arg1 == '--quantize' || $arg1 == '-q' ]]; then
./quantize $arg2
elif [[ $arg1 == '--run' || $arg1 == '-r' ]]; then
@@ -32,7 +32,7 @@ else
echo " --run (-r): Run a model previously converted into ggml"
echo " ex: -m /models/7B/ggml-model-q4_0.bin -p \"Building a website can be done in 10 simple steps:\" -n 512"
echo " --convert (-c): Convert a llama model into ggml"
echo " ex: \"/models/7B/\" 1"
echo " ex: --outtype f16 \"/models/7B/\" "
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 " --all-in-one (-a): Execute --convert & --quantize"