Dockerfile

FROM nvidia/cuda:12.1.0-devel-ubuntu22.04

# Set environment variables
ENV DEBIAN_FRONTEND=noninteractive
ENV PYTHONUNBUFFERED=1
ENV HF_HOME=/app/.cache/huggingface
ENV TRANSFORMERS_CACHE=/app/.cache/huggingface/transformers

# Install system dependencies
RUN apt-get update && apt-get install -y \
    python3.11 \
    python3.11-dev \
    python3-pip \
    git \
    wget \
    curl \
    ninja-build \
    && rm -rf /var/lib/apt/lists/*

# Set Python 3.11 as default
RUN update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.11 1

# Upgrade pip
RUN pip3 install --upgrade pip setuptools wheel

# Install PyTorch with CUDA 12.1
RUN pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121

# Install core ML packages
RUN pip3 install \
    transformers>=4.36.0 \
    accelerate>=0.25.0 \
    datasets>=2.16.0 \
    peft>=0.7.0 \
    trl>=0.7.0 \
    bitsandbytes>=0.41.0 \
    huggingface_hub>=0.20.0

# Install Flash Attention 2
RUN pip3 install flash-attn --no-build-isolation

# Install DeepSpeed for distributed training
RUN pip3 install deepspeed

# Install additional utilities
RUN pip3 install \
    einops \
    sentencepiece \
    protobuf \
    scipy \
    wandb \
    tensorboard \
    tqdm

# Set working directory
WORKDIR /app

# Copy application files
COPY . /app/

# Create cache directories
RUN mkdir -p /app/.cache/huggingface

# Set entrypoint
CMD ["python3", "app.py"]