# Containerfile for running deepspeed training FROM nvcr.io/nvidia/cuda:12.1.1-cudnn8-devel-ubi9 ARG VENDOR='' LABEL vendor=${VENDOR} LABEL org.opencontainers.image.vendor=${VENDOR} RUN dnf install -y python python-devel git RUN python -m ensurepip --upgrade RUN pip3 install torch==2.1.2 --index-url https://download.pytorch.org/whl/cu121 RUN pip3 install packaging wheel RUN pip3 install flash-attn==2.5.7 RUN pip3 install deepspeed==0.14.2 RUN pip3 install transformers==4.40.1 RUN pip3 install ipdb jupyterlab gpustat matplotlib hydra-core datasets rich numba RUN git clone https://github.com/instructlab/training.git RUN mkdir -p /ilab-data/training_output WORKDIR /training CMD ["/bin/bash"]