| 1234567891011121314151617181920 |
- ARG FROM_IMAGE_NAME=nvcr.io/nvidia/paddlepaddle:23.06-py3
- FROM ${FROM_IMAGE_NAME}
- RUN apt-get update && apt-get install -y pbzip2 pv bzip2 cabextract
- ENV BERT_PREP_WORKING_DIR /workspace/bert/data
- WORKDIR /workspace/
- WORKDIR /workspace/bert
- RUN pip install --no-cache-dir \
- tqdm boto3 requests six ipdb h5py nltk progressbar tokenizers>=0.7\
- git+https://github.com/NVIDIA/dllogger wget
- RUN apt-get install -y iputils-ping
- COPY . .
- RUN apt-get install -y libjemalloc-dev
- RUN pip install git+https://github.com/NVIDIA/lddl.git
- RUN python -m nltk.downloader punkt
|