docker image ghcr.io/ggerganov/llama.cpp:light not working

[dnalexen]

The docker image ghcr.io/ggerganov/llama.cpp:light no longer works. It exits without giving the answer.

[prusnak]

What is the exact command line you use?

[dnalexen]

I used this command:
docker run -v /llama/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

[prusnak]

This works for me. You need to have the model files downloaded in /llama/models.