Dockerfile

# Use the official llama.cpp full 
FROM ghcr.io/ggml-org/llama.cpp:full
RUN apt update && apt install wget -y
RUN wget "https://huggingface.co/mradermacher/StrawberryLemonade-L3-70B-v1.0-i1-GGUF/resolve/main/StrawberryLemonade-L3-70B-v1.0.i1-IQ2_M.gguf" -O /StrawberryLemonade-L3-70B-v1.0.i1-IQ2_M.gguf
CMD ["--server", "-m", "/StrawberryLemonade-L3-70B-v1.0.i1-IQ2_M.gguf", "--port", "7860", "--host", "0.0.0.0", "-n", "512", "--no-warmup"]