Dockerfile

FROM ghcr.io/ggerganov/llama.cpp:full

ARG MODEL_URL=https://huggingface.co/Nan-Do/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B-GGUF/resolve/main
ARG MODEL_NAME=Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B-Q4_0.gguf

ENV DEBIAN_FRONTEND=noninteractive

WORKDIR /app

# Update and install necessary dependencies
RUN apt update && \
    apt install --no-install-recommends -y \
        build-essential \
        python3 \
        python3-pip \
        wget \
        curl \
        git \
        cmake \
        zlib1g-dev \
        libblas-dev && \
    apt clean && \
    rm -rf /var/lib/apt/lists/*

# Use the variables for the model URL and name
RUN wget ${MODEL_URL}/${MODEL_NAME}

RUN make

# Expose the port
EXPOSE 8080

# Use the model name variable in CMD as well
CMD ["--server", "--model", "${MODEL_NAME}", "--threads", "10", "--host", "0.0.0.0"]