aditya/llama.cpp
1
0
Fork 0
mirror of https://git.adityakumar.xyz/llama.cpp.git synced 2024-11-09 15:29:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

docker : add '--server' option (#2174)

Browse source
This commit is contained in:
Jinwoo Jeong 2023-07-12 01:12:35 +09:00 committed by GitHub
parent 917831c63a
commit 3ec7e596b2
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
.devops/tools.sh
View file

@ -26,6 +26,8 @@ elif [[ $arg1 == '--all-in-one' || $arg1 == '-a' ]]; then
./quantize "$i" "${i/f16/q4_0}" q4_0
fi
done
elif [[ $arg1 == '--server' || $arg1 == '-s' ]]; then
./server $arg2
else
echo "Unknown command: $arg1"
echo "Available commands: "
@ -37,4 +39,6 @@ else
echo " ex: \"/models/7B/ggml-model-f16.bin\" \"/models/7B/ggml-model-q4_0.bin\" 2"
echo " --all-in-one (-a): Execute --convert & --quantize"
echo " ex: \"/models/\" 7B"
echo " --server (-s): Run a model on the server"
echo " ex: -m /models/7B/ggml-model-q4_0.bin -c 2048 -ngl 43 -mg 1 --port 8080"
fi