Revert "Default to using tokenizer eos and bos in convert_text_to_mds… #361
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: Docker | |
| on: | |
| push: | |
| branches: | |
| - main | |
| pull_request: | |
| branches: | |
| - main | |
| paths: | |
| - ./Dockerfile | |
| - .github/workflows/docker.yaml | |
| workflow_dispatch: {} | |
| jobs: | |
| docker-build: | |
| runs-on: ubuntu-latest | |
| if: github.repository_owner == 'mosaicml' | |
| strategy: | |
| matrix: | |
| include: | |
| - name: '2.1.0_cu121' | |
| base_image: mosaicml/pytorch:2.1.0_cu121-python3.10-ubuntu20.04 | |
| dep_groups: '[gpu]' | |
| - name: '2.1.0_cu121_flash2' | |
| base_image: mosaicml/pytorch:2.1.0_cu121-python3.10-ubuntu20.04 | |
| dep_groups: '[gpu-flash2]' | |
| - name: '2.1.0_cu121_aws' | |
| base_image: mosaicml/pytorch:2.1.0_cu121-python3.10-ubuntu20.04-aws | |
| dep_groups: '[gpu]' | |
| - name: '2.1.0_cu121_flash2_aws' | |
| base_image: mosaicml/pytorch:2.1.0_cu121-python3.10-ubuntu20.04-aws | |
| dep_groups: '[gpu-flash2]' | |
| steps: | |
| - name: Maximize Build Space on Worker | |
| uses: easimon/maximize-build-space@v4 | |
| with: | |
| overprovision-lvm: true | |
| remove-dotnet: true | |
| remove-android: true | |
| remove-haskell: true | |
| - name: Checkout | |
| uses: actions/checkout@v3 | |
| - name: Setup QEMU | |
| uses: docker/setup-qemu-action@v2 | |
| - name: Setup Docker Buildx | |
| uses: docker/setup-buildx-action@v2 | |
| - name: Login to DockerHub | |
| uses: docker/login-action@v2 | |
| with: | |
| username: ${{ secrets.DOCKER_HUB_USERNAME }} | |
| password: ${{ secrets.DOCKER_HUB_PASSWORD }} | |
| - name: Calculate Docker Image Variables | |
| run: | | |
| set -euxo pipefail | |
| ################### | |
| # Calculate the tag | |
| ################### | |
| GIT_SHA=$(echo ${{ github.sha }} | cut -c1-7) | |
| echo "IMAGE_TAG=${GIT_SHA}" >> ${GITHUB_ENV} | |
| if [ "${{ github.event_name }}" == "pull_request" ]; then | |
| echo "Triggered by pull_request event." | |
| STAGING_REPO="mosaicml/ci-staging" | |
| IMAGE_TAG="${STAGING_REPO}:${{matrix.name}}-${GIT_SHA}" | |
| IMAGE_CACHE="${STAGING_REPO}:${{matrix.name}}-buildcache" | |
| else | |
| # Triggered by push or workflow_dispatch event | |
| echo "Triggered by ${{ github.event_name }} event, releasing to prod" | |
| PROD_REPO="mosaicml/llm-foundry" | |
| IMAGE_TAG="${PROD_REPO}:${{matrix.name}}-${GIT_SHA},${PROD_REPO}:${{matrix.name}}-latest" | |
| IMAGE_CACHE="${PROD_REPO}:${{matrix.name}}-buildcache" | |
| fi | |
| echo "IMAGE_TAG=${IMAGE_TAG}" >> ${GITHUB_ENV} | |
| echo "IMAGE_CACHE=${IMAGE_CACHE}" >> ${GITHUB_ENV} | |
| - name: Build and Push the Docker Image | |
| uses: docker/build-push-action@v3 | |
| with: | |
| context: . | |
| tags: ${{ env.IMAGE_TAG }} | |
| push: true | |
| cache-from: type=registry,ref=${{ env.IMAGE_CACHE }} | |
| cache-to: type=registry,ref=${{ env.IMAGE_CACHE }},mode=max | |
| build-args: | | |
| BASE_IMAGE=${{ matrix.base_image }} | |
| DEP_GROUPS=${{ matrix.dep_groups }} |