File size: 2,396 Bytes
b269c5d b9cb4a6 b269c5d b9cb4a6 b269c5d b9cb4a6 b269c5d b9cb4a6 b269c5d b9cb4a6 f2adbf5 b269c5d b9cb4a6 b269c5d |
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 64 65 66 67 68 |
# Use Python 3.10 base image optimized for HuggingFace Spaces
FROM python:3.10-slim
# Set working directory
WORKDIR /app
# Install system dependencies required for runtime and compilation
RUN apt-get update && apt-get install -y \
wget \
curl \
git \
git-lfs \
build-essential \
cmake \
libopenblas-dev \
libssl-dev \
libgomp1 \
&& rm -rf /var/lib/apt/lists/*
# Initialize git-lfs
RUN git lfs install
# Set environment variables for optimal Docker performance
ENV PYTHONUNBUFFERED=1
ENV PYTHONDONTWRITEBYTECODE=1
ENV PIP_NO_CACHE_DIR=1
ENV DOCKER_CONTAINER=true
# Create models directory
RUN mkdir -p /app/models
# Copy and install llama-cpp-python from local wheel
COPY wheels/llama_cpp_python-0.3.16-cp310-cp310-linux_x86_64.whl /tmp/
RUN pip install /tmp/llama_cpp_python-0.3.16-cp310-cp310-linux_x86_64.whl
# Copy requirements first for better Docker layer caching
COPY requirements.txt .
# Install Python dependencies
RUN pip install --no-cache-dir -r requirements.txt
# Copy configuration to get model info
COPY config.py .
# Pre-download the model during build
RUN python -c "import os; from huggingface_hub import hf_hub_download; from config import Config; os.makedirs('/app/models', exist_ok=True); print(f'Downloading model {Config.MODEL_REPO}/{Config.MODEL_FILENAME}...'); p=hf_hub_download(repo_id=Config.MODEL_REPO, filename=Config.MODEL_FILENAME, local_dir='/app/models', token=os.getenv('HUGGINGFACE_TOKEN') or None); print(f'Model downloaded to: {p}'); import os; s=os.path.getsize(p) if os.path.exists(p) else (_ for _ in ()).throw(FileNotFoundError(f'Model file not found: {p}')); print(f'Model file size: {s/(1024**3):.2f} GB'); (s>1024*1024) or (_ for _ in ()).throw(ValueError(f'Downloaded model file seems too small: {s} bytes')); print('Model download verification successful')"
# Verify model file exists after build
RUN ls -la /app/models/ && \
[ -n "$(ls /app/models/*.gguf 2>/dev/null)" ] || (echo "No .gguf model file found!" && exit 1)
# Copy application files
COPY . .
# Make entrypoint script executable
RUN chmod +x entrypoint.sh
# Create a non-root user for security
RUN useradd -m -u 1000 user && chown -R user:user /app
USER user
# Expose the port that Gradio will run on
EXPOSE 7860
# Set entrypoint and default command
# ENTRYPOINT ["./entrypoint.sh"]
CMD ["python", "main.py", "--mode", "gradio"]
|