init

.github/workflows/main.yml

@@ -0,0 +1,19 @@
+name: Sync to Hugging Face hub
+on:
+  push:
+    branches: [main]
+  # to run this workflow manually from the Actions tab
+  workflow_dispatch:
+
+jobs:
+  sync-to-hub:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+          lfs: true
+      - name: Push to hub
+        env:
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        run: git push https://mteb:[email protected]/datasets/mteb/results main

CONTRIBUTING

@@ -0,0 +1,3 @@
+TODO
+
+Users must be sure no files are over 10MB. If there are we should remove all spaces from them to keep them < 10MB. This should be a pre-commit hook checking.

README.md

@@ -0,0 +1,5 @@
+---
+benchmark: mteb
+type: evaluation
+submission_name: MTEB
+---

remove_spaces_from_large_json_files.py

@@ -0,0 +1,15 @@
+import os
+import glob
+import sys
+import json
+
+for file in glob.glob("results/*/*/*.json"):
+    # if the file is greater than 9 MB, compress it with gzip
+    if os.path.getsize(file) >= 9.5 * 1024 * 1024:
+        print(f"Resizing {file} to have no indentations")
+        # read it in as json and write it out with no indent
+        with open(file, "r") as f:
+            data = json.load(f)
+
+        with open(file, "w") as f:
+            json.dump(data, f, indent=None)