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

Update REAMDE.md (#1673)

Browse source
This commit is contained in:
qingfengfenga 2023-06-05 11:06:18 +08:00
parent 5eed33f3b3
commit 80891d1591
1 changed files with 2 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

3
README.md
View file

@ -663,8 +663,9 @@ or with a light image:
docker run -v /path/to/models:/models ghcr.io/ggerganov/llama.cpp:light -m /models/7B/ggml-model-q4_0.bin -p "Building a website can be done in 10 simple steps:" -n 512
```
If you want to use Chinese model, use this command.
> more options [#1673](https://github.com/ggerganov/llama.cpp/pull/1673)
```
docker run -v /path/to/models:/models -e LC_ALL=zh_CN.utf8 ghcr.io/ggerganov/llama.cpp:full --run -m /models/7B/ggml-model-q4_0.bin -p "Building a website can be done in 10 simple steps:" -n 512
docker run -v /path/to/models:/models -e LANG=C.utf8 ghcr.io/ggerganov/llama.cpp:full --run -m /models/7B/ggml-model-q4_0.bin -p "Building a website can be done in 10 simple steps:" -n 512
```
### Contributing