File size: 1,037 Bytes
47ed1f0 124675b 4846749 124675b e0044e5 47ed1f0 4846749 47ed1f0 4846749 124675b e0044e5 4846749 124675b 4846749 e0044e5 4846749 124675b e0044e5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 | FROM ghcr.io/ggml-org/llama.cpp:full
WORKDIR /app
# Install Python
RUN apt-get update && \
apt-get install -y --no-install-recommends \
python3 \
python3-pip \
python3-venv && \
rm -rf /var/lib/apt/lists/*
# Python virtual environment
RUN python3 -m venv /opt/venv
ENV PATH="/opt/venv/bin:${PATH}"
# Install Hugging Face Hub
RUN pip install --no-cache-dir --upgrade pip huggingface_hub
# Download DeepSeek Coder V2 Lite Instruct GGUF
RUN python3 - <<'PY'
from huggingface_hub import hf_hub_download
hf_hub_download(
repo_id="bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF",
filename="DeepSeek-Coder-V2-Lite-Instruct-Q4_K_M.gguf",
local_dir="/app"
)
PY
CMD [
"--server",
"-m",
"/app/DeepSeek-Coder-V2-Lite-Instruct-Q4_K_M.gguf",
"--host",
"0.0.0.0",
"--port",
"7860",
"-t",
"4",
"-b",
"1024",
"-c",
"16384",
"-n",
"4096",
"--parallel",
"1",
"--cache-type-k",
"q8_0",
"--cache-type-v",
"q8_0"
] |