ARG FROM_IMAGE_NAME=nvcr.io/nvidia/pytorch:20.12-py3
FROM ${FROM_IMAGE_NAME}
RUN apt-get update \
&& apt-get install -y --no-install-recommends \
bzip2 \
cabextract \
iputils-ping \
pbzip2 \
pv \
&& rm -rf /var/lib/apt/lists/*
WORKDIR /workspace/bert
COPY requirements.txt .
RUN pip install --no-cache-dir https://github.com/mlperf/logging/archive/9ea0afa.zip \
&& pip install --no-cache-dir -r requirements.txt
RUN git clone https://github.com/attardi/wikiextractor.git \
&& cd wikiextractor && git checkout e4abb4cbd019b0257824ee47c23dd163919b731b
ENV BERT_PREP_WORKING_DIR /workspace/bert/data
WORKDIR /workspace/bert
COPY . .
ENV PYTHONPATH "/workspace/bert"
RUN cd /workspace/bert/mhalib && python setup.py build && cp build/lib*/mhalib* ../