Dockerfile

# Use the official Python 3.12 image as a base
FROM python:3.12-slim

# Set environment variables to prevent Python from writing .pyc files and buffering stdout/stderr
ENV PYTHONDONTWRITEBYTECODE=1
ENV PYTHONUNBUFFERED=1

# Install system dependencies
RUN apt-get update && apt-get install -y \
    build-essential \
    git \
    wget \
    curl \
    unzip \
    && rm -rf /var/lib/apt/lists/*

# Create a working directory
WORKDIR /app

# Create cache directory with proper permissions
RUN mkdir -p /app/cache && chmod -R 777 /app/cache
RUN mkdir -p /app/output && chmod -R 777 /app/output

# Set the cache environment variable
ENV HF_HOME=/app/cache

# Install Python dependencies
RUN git clone https://github.com/facebookresearch/MobileLLM
RUN pip install --upgrade pip
RUN pip install -r requirement.txt

# Copy the current directory contents into the container at /app
COPY . /app

# Unzip the data.zip file into the /app/data directory
RUN unzip data.zip -d /app/data

# data pre-process and specify the data path in pretrain.sh
# run pretraining
RUN sudo bash pretrain.sh