Create .github/workflows/evaluate.yml

.github/workflows/evaluate.yml

@@ -0,0 +1,34 @@
+name: Model Evaluation
+on:
+  workflow_dispatch:
+  schedule:
+    - cron: '0 0 * * *'  # Run daily at midnight UTC
+
+jobs:
+  evaluate:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+      
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: '3.9'
+          
+      - name: Install dependencies
+        run: |
+          pip install -r requirements.txt
+          
+      - name: Run evaluation
+        env:
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        run: |
+          python scripts/run_evaluation.py
+          
+      - name: Commit and push results
+        run: |
+          git config --local user.email "[email protected]"
+          git config --local user.name "GitHub Action"
+          git add benchmark_results/*
+          git commit -m "Update evaluation results" || exit 0
+          git push