ggml-coding-cpu / Dockerfile
matthoffner's picture
Create Dockerfile
f0d9981 verified
raw
history blame
730 Bytes
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/matthoffner/Magicoder-S-DS-6.7B-GGUF/resolve/main/Magicoder-S-DS-6.7B_Q4_K_M.gguf
RUN make
# Expose the port
EXPOSE 8080
# Start the llava-server with models
CMD ["--server", "--model", "Magicoder-S-DS-6.7B_Q4_K_M.gguf", "--threads", "6", "--host", "0.0.0.0", "-ngl", "33"]