rebuild docs #49
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: All Tokenizer Checks | |
| on: | |
| push: | |
| paths: | |
| - 'maze_dataset/utils.py' # temporary | |
| - 'maze_dataset/token_utils.py' # temporary | |
| - 'maze_dataset/constants.py' | |
| - 'maze_dataset/tokenization/*.py' | |
| - 'maze_dataset/tokenization/MazeTokenizerModular_hashes.npz' | |
| - 'notebooks/demo_mazetokenizermodular.ipynb' | |
| - 'tests/all_tokenizers/*.py' | |
| - 'pyproject.toml' # on new version or update deps | |
| - '.github/workflows/all-tok-checks.yml' # changing this file | |
| - '.lastversion' # on new release | |
| workflow_dispatch: | |
| inputs: | |
| n_to_test: | |
| description: 'Number of tokenizers to test' | |
| required: false | |
| default: 5000 | |
| type: number | |
| pytest_parallel: | |
| description: '1 to parallelize tests with -n auto, to run without parallelization' | |
| required: false | |
| default: 1 | |
| type: number | |
| jobs: | |
| all_tok_test: | |
| name: All Tokenizer Tests | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - uses: actions/setup-python@v5 | |
| with: | |
| python-version: "3.10" | |
| - name: Install dependencies | |
| run: | | |
| curl -sSL https://install.python-poetry.org | python3 - | |
| poetry lock --check | |
| poetry install | |
| - name: tokenizer hash tests | |
| run: | | |
| make test_tok_hashes | |
| - name: all tokenizer tests | |
| run: | | |
| N_TO_TEST=${{ github.event.inputs.n_to_test || '5000' }} | |
| PYTEST_PARALLEL=${{ github.event.inputs.pytest_parallel || '1' }} | |
| make test_all_tok SKIP_HASH_TEST=1 NUM_TOKENIZERS_TO_TEST=$N_TO_TEST PYTEST_PARALLEL=$PYTEST_PARALLEL |