sayshara's picture
Serve base Nemotron 3 Nano without LoRA
7f28039 verified
Raw
History Blame Contribute Delete
619 Bytes
FROM ghcr.io/ggml-org/llama.cpp:server-cuda
ENV MODEL_REPO=mradermacher/NVIDIA-Nemotron-3-Nano-4B-BF16-GGUF
ENV MODEL_FILE=NVIDIA-Nemotron-3-Nano-4B-BF16.Q4_K_M.gguf
ENV PORT=7860
ENV CTX_SIZE=2048
ENV N_GPU_LAYERS=99
ENV NO_WARMUP=1
ENV HF_XET_HIGH_PERFORMANCE=1
USER root
RUN apt-get update \
&& apt-get install -y --no-install-recommends python3 python3-pip ca-certificates \
&& rm -rf /var/lib/apt/lists/* \
&& python3 -m pip install --break-system-packages --no-cache-dir "huggingface_hub"
COPY start_server.py /app/start_server.py
EXPOSE 7860
ENTRYPOINT []
CMD ["python3", "/app/start_server.py"]