| # MiniMind Max2 - Efficient Edge LLM | |
| # Docker Hub: sultanafariabd/minimind-max2 | |
| FROM python:3.11-slim | |
| LABEL maintainer="MiniMind Team <contact@minimind.ai>" | |
| LABEL org.opencontainers.image.title="MiniMind Max2" | |
| LABEL org.opencontainers.image.description="Efficient LLM with MoE (8 experts, 25% activation) + GQA" | |
| LABEL org.opencontainers.image.version="1.0.0" | |
| LABEL org.opencontainers.image.source="https://huggingface.co/fariasultana/MiniMind" | |
| LABEL org.opencontainers.image.licenses="Apache-2.0" | |
| LABEL ai.model.architecture="MoE+GQA" | |
| LABEL ai.model.parameters="500M-3B" | |
| LABEL ai.model.active_ratio="25%" | |
| ENV PYTHONUNBUFFERED=1 | |
| ENV MODEL_VARIANT=max2-nano | |
| ENV PORT=8000 | |
| WORKDIR /app | |
| # Install dependencies | |
| RUN pip install --no-cache-dir \ | |
| torch>=2.1.0 \ | |
| numpy>=1.24.0 \ | |
| fastapi>=0.100.0 \ | |
| uvicorn>=0.23.0 \ | |
| safetensors>=0.4.0 \ | |
| pydantic>=2.0.0 | |
| # Copy application | |
| COPY serve.py /app/ | |
| COPY model_info.json /app/ | |
| EXPOSE 8000 | |
| HEALTHCHECK --interval=30s --timeout=10s --start-period=30s \ | |
| CMD python -c "import urllib.request; urllib.request.urlopen('http://localhost:8000/health')" || exit 1 | |
| CMD | |