commit ca111905946cda2f2de452289c2828c3ea9b468f parent a0525f71a196ff27218fc2a32fdaa0a52d05aceb Author: Amit Dutta <mail@amit.is-a.dev> Date: Sun, 7 Jun 2026 16:32:14 +0530 Modify sync workflow to filter large files Updated the workflow to filter out large compiler binaries before syncing to Hugging Face. Diffstat:
| M | .github/workflows/sync-to-hf.yml | | | 20 | ++++++++++++++------ |
1 file changed, 14 insertions(+), 6 deletions(-)
diff --git a/.github/workflows/sync-to-hf.yml b/.github/workflows/sync-to-hf.yml @@ -1,10 +1,10 @@ name: Manual and Auto Sync to Hugging Face on: - workflow_dispatch: + workflow_dispatch: push: branches: - - main + - main jobs: sync-dataset: @@ -13,11 +13,19 @@ jobs: - name: Checkout Repository uses: actions/checkout@v4 with: - fetch-depth: 0 + fetch-depth: 0 - - name: Force Sync to Hugging Face Dataset + - name: Filter Large Files and Sync to Hugging Face env: HF_TOKEN: ${{ secrets.HF_TOKEN }} run: | - # Configures git and force-pushes the exact current repository state over to Hugging Face - git push --force https://notamitgamer:$HF_TOKEN@huggingface.co/datasets/notamitgamer/usercontent main:main + git config user.name "github-actions[bot]" + git config user.email "github-actions[bot]@users.noreply.github.com" + + git rm -rf --cached MinGW64 || true + + find . -name "*.exe" -exec git rm --cached {} + || true + + git commit -m "Filter out large compiler binaries for HF sync" || true + + git push --force https://notamitgamer:$HF_TOKEN@huggingface.co/datasets/notamitgamer/usercontent HEAD:main