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

ENV DEBIAN_FRONTEND=noninteractive

# 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/*

WORKDIR /app

RUN wget https://huggingface.co/brittlewis12/Snorkel-Mistral-PairRM-DPO-GGUF/resolve/main/snorkel-mistral-pairrm-dpo.Q4_K_M.gguf

RUN make

# Expose the port
EXPOSE 8080

# Use the model name variable in CMD as well
CMD ["--server", "--model", "snorkel-mistral-pairrm-dpo.Q4_K_M.gguf", "--threads", "8", "--host", "0.0.0.0"]