From cf347dfe350aa64f6f2d51df677379fce35284e4 Mon Sep 17 00:00:00 2001
From: pculliton <phillipculliton@gmail.com>
Date: Fri, 17 May 2024 16:06:03 -0400
Subject: [PATCH] Adds Kaggle testing to CI workflow

Using a restricted Kaggle account, this code:
- Adds an Ubuntu 20.04 build (required for glibc compat with Kaggle infra)
- Uploads the ubuntu-20.04 build and supporting library to a Kaggle dataset using a fork of `push-kaggle-dataset`
- Creates a new version of a Kaggle notebook that loads artifacts from the Kaggle Model Hub, along with the newly updated dataset, and validates a 2b-it-sfp model.
- Runs the notebook and throws an error if the process does not complete, raises an exception, or produces an invalid response.

Todo: add tests / capabilities to the smoke tests used by the notebook.
---
 .github/workflows/build.yml | 42 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 41 insertions(+), 1 deletion(-)

diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
index 2635ec5..bb7783a 100644
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -17,10 +17,12 @@ jobs:
       fail-fast: false
       matrix:
         # When adding another, also add to copybara's github_check_runs.
-        os: ['ubuntu-latest', 'macos-latest', 'windows-latest']
+        os: ['ubuntu-latest', 'macos-latest', 'windows-latest', 'ubuntu-20.04']
         build_type: ['Release']
         preset: ['make', 'windows']
         exclude:
+          - os: ubuntu-20.04
+            preset: windows
           - os: ubuntu-latest
             preset: windows
           - os: macos-latest
@@ -60,6 +62,44 @@ jobs:
           ${{ github.workspace }}/build/gemma
           ${{ github.workspace }}/build/libgemma.a
 
+    - if: matrix.os == 'ubuntu-20.04'
+      name: Upload build artifacts to Kaggle
+      uses: pculliton/push-kaggle-dataset@v1.0.0
+      env:
+        KAGGLE_USERNAME: ${{ secrets.KAGGLE_USERNAME }}
+        KAGGLE_KEY: ${{ secrets.KAGGLE_KEY }}
+      with:
+        id:  "phillipculliton/gemma-build-artifacts"
+        files: |
+          build/gemma
+          build/_deps/sentencepiece-build/src/libsentencepiece.so.0
+
+    - if: matrix.os == 'ubuntu-20.04'
+      name: Create code for new test notebook version
+      run: |
+        cat > runner.py << EOF
+        import subprocess
+        subprocess.run(["cp", "/kaggle/input/gemma-build-artifacts/gemma", "/kaggle/working"])
+        subprocess.run(["chmod", "700", "/kaggle/working/gemma"])
+        subprocess.run(["cp", "/kaggle/input/gemma-build-artifacts/_deps/sentencepiece-build/src/libsentencepiece.so.0", "/kaggle/working"])
+        output = subprocess.run(["/kaggle/working/gemma", "--tokenizer", "/kaggle/input/gemma/gemmacpp/2b-it-sfp/4/tokenizer.spm", "--compressed_weights", "/kaggle/input/gemma/gemmacpp/2b-it-sfp/4/2b-it-sfp.sbs", "--model", "2b-it", "--verbosity", "0", "--max_generated_tokens", "128"], stdout=subprocess.PIPE, input='Write an email to the moon.', encoding='ascii').stdout
+        assert("write an email to the moon." not in output.lower());
+        assert("moon" in output.lower());
+        EOF
+      
+    - if: matrix.os == 'ubuntu-20.04'
+      name: Run kaggle test notebook
+      uses: pculliton/kaggle-action@v1.0.28
+      with:
+        username: ${{ secrets.KAGGLE_USERNAME }}
+        key: ${{ secrets.KAGGLE_KEY }}
+        title: GemmaCPP-CI-2
+        code_file: runner.py
+        dataset_sources: "phillipculliton/gemma-build-artifacts"
+        model_sources: "google/gemma/gemmaCpp/2b-it-sfp/4"
+        enable_gpu: False
+        kernel_type: script
+
   bazel:
     runs-on: ubuntu-latest
     steps: