Spaces:
Sleeping
Sleeping
Download Dockerfile from mjpsm/activity-instruction-api: direct link, hf CLI and curl.
- Browser
- Download file 719 Bytes
-
https://huggingface.co/spaces/mjpsm/activity-instruction-api/resolve/main/Dockerfile
- Command line
-
hf download hf://spaces/mjpsm/activity-instruction-api/Dockerfile
-
curl -L -o Dockerfile https://huggingface.co/spaces/mjpsm/activity-instruction-api/resolve/main/Dockerfile
719 Bytes
| FROM python:3.11-slim | |
| ENV PYTHONDONTWRITEBYTECODE=1 | |
| ENV PYTHONUNBUFFERED=1 | |
| ENV PIP_NO_CACHE_DIR=1 | |
| RUN apt-get update \ | |
| && apt-get install -y --no-install-recommends libgomp1 \ | |
| && rm -rf /var/lib/apt/lists/* | |
| WORKDIR /app | |
| COPY requirements.txt /app/requirements.txt | |
| # Identical prebuilt CPU-wheel approach to the Composition API. | |
| # NOTE: If the wheel cannot load Qwen3.5 GGUF, upgrade llama-cpp-python. | |
| RUN pip install --upgrade pip \ | |
| && pip install --prefer-binary \ | |
| --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu \ | |
| -r /app/requirements.txt | |
| COPY main.py /app/main.py | |
| EXPOSE 7860 | |
| CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860", "--workers", "1"] | |