fix: Enforce revision ID and model names for future contributions (#56)

Added this change mainly due to duplicates models results and due to recent addition not including a model revision (which I we should probably discourage).

This fixes models results for:
- voyage

README.md

@@ -4,6 +4,10 @@ type: evaluation
 submission_name: MTEB
 ---
 
+> [!NOTE]  
+> Previously it was possible to submit models results to MTEB by adding the results to the model metadata. This is no longer an option as we want to ensure high quality metadata.
+
+
 This repository contain the results of the embedding benchmark evaluated using the package `mteb`.
 
 

paths.json

@@ -14632,10 +14632,6 @@
     "results/vesteinn__DanskBERT/no_revision_available/LccSentimentClassification.json",
     "results/vesteinn__DanskBERT/no_revision_available/DalajClassification.json"
   ],
-  "voyage-multilingual-2": [
-    "results/voyage-multilingual-2/1/BornholmBitextMining.json",
-    "results/voyage-multilingual-2/1/STSB.json"
-  ],
   "voyageai__voyage-2": [
     "results/voyageai__voyage-2/no_revision_available/MassiveIntentClassification.json",
     "results/voyageai__voyage-2/no_revision_available/MLSUMClusteringP2P.json",
@@ -15003,6 +14999,8 @@
     "results/voyageai__voyage-lite-02-instruct/no_revision_available/StackOverflowDupQuestions.json"
   ],
   "voyageai__voyage-multilingual-2": [
+    "results/voyageai__voyage-multilingual-2/1/BornholmBitextMining.json",
+    "results/voyageai__voyage-multilingual-2/1/STSB.json"
     "results/voyageai__voyage-multilingual-2/no_revision_available/MassiveIntentClassification.json",
     "results/voyageai__voyage-multilingual-2/no_revision_available/LEMBWikimQARetrieval.json",
     "results/voyageai__voyage-multilingual-2/no_revision_available/MLSUMClusteringP2P.json",

results/voyageai__voyage-3-lite/no_revision_available/model_meta.json

@@ -1 +1 @@
-{"name": "voyageai__voyage-3-lite", "revision": "no_revision_available", "release_date": "2024-09-22", "languages": null, "n_parameters": null, "memory_usage": null, "max_tokens": 32000, "embed_dim": 512, "license": null, "open_source": false, "similarity_fn_name": null, "framework": [], "loader": "VoyageWrapper"}
+{"name": "voyageai/voyage-3-lite", "revision": "no_revision_available", "release_date": "2024-09-22", "languages": null, "n_parameters": null, "memory_usage": null, "max_tokens": 32000, "embed_dim": 512, "license": null, "open_source": false, "similarity_fn_name": null, "framework": [], "loader": "VoyageWrapper"}

results/voyageai__voyage-3/no_revision_available/model_meta.json

@@ -1 +1 @@
-{"name": "voyageai__voyage-3", "revision": "no_revision_available", "release_date": "2024-09-22", "languages": null, "n_parameters": null, "memory_usage": null, "max_tokens": 32000, "embed_dim": 1024, "license": null, "open_source": false, "similarity_fn_name": null, "framework": [], "loader": "VoyageWrapper"}
+{"name": "voyageai/voyage-3", "revision": "no_revision_available", "release_date": "2024-09-22", "languages": null, "n_parameters": null, "memory_usage": null, "max_tokens": 32000, "embed_dim": 1024, "license": null, "open_source": false, "similarity_fn_name": null, "framework": [], "loader": "VoyageWrapper"}

results/voyageai__voyage-multilingual-2/1/model_meta.json

@@ -0,0 +1 @@
+{"name": "voyageai/voyage-multilingual-2", "revision": "1", "release_date": "2024-06-10", "languages": null, "n_parameters": null, "memory_usage": null, "max_tokens": 32000, "embed_dim": 1024, "license": null, "open_source": false, "similarity_fn_name": null, "framework": [], "loader": "VoyageWrapper"}

tests/test_ensure_correct_metadata.py

@@ -0,0 +1,73 @@
+import json
+
+import pytest
+
+from tests.test_correct_folder_structure import folders_without_meta, results_folder
+
+model_rev_pairs = [
+    (model_folder, rev_folder)
+    for model_folder in results_folder.glob("*")
+    for rev_folder in model_folder.glob("*")
+    if model_folder.name not in [".DS_Store"]
+    and rev_folder.name not in [".DS_Store"]
+    and ((model_folder.name, rev_folder.name) not in folders_without_meta)
+]
+
+
+@pytest.mark.parametrize("model_rev_pair", model_rev_pairs)
+def test_model_meta_in_folders(model_rev_pair):
+    """
+    Models added after the 26th of November should contain a model_meta.json file
+    """
+    model_folder, rev_folder = model_rev_pair
+
+    meta_file = rev_folder / "model_meta.json"
+    assert meta_file.exists()
+    assert meta_file.is_file()
+    assert meta_file.parent == rev_folder
+    assert meta_file.suffix == ".json"
+    assert meta_file.stem == "model_meta"
+
+
+# please do not add to this list, this is only for historic results, all new results should include a revision ID
+revision_exceptions = [
+    ("castorini__mdpr-tied-pft-msmarco", "no_revision_available"),
+    ("voyageai__voyage-3", "no_revision_available"),
+    ("sentence-transformers__all-mpnet-base-v2", "no_revision_available"),
+    ("Snowflake__snowflake-arctic-embed-m-v1.5", "no_revision_available"),
+    ("sentence-transformers__all-MiniLM-L12-v2", "no_revision_available"),
+    ("nthakur__mcontriever-base-msmarco", "no_revision_available"),
+    ('voyageai__voyage-3-lite', 'no_revision_available')
+]
+
+
+@pytest.mark.parametrize("model_rev_pair", model_rev_pairs)
+def test_revision_is_specified_for_new_additions(model_rev_pair):
+    """
+    Models added after 26th of November should include a revision ID and can not use the "no_revision_available" fallback.
+    """
+    model_folder, rev_folder = model_rev_pair
+    if (model_folder.name, rev_folder.name) not in revision_exceptions:
+        meta_file = rev_folder / "model_meta.json"
+        with meta_file.open("r") as f:
+            meta = json.load(f)
+        assert meta["revision"].lower() not in [
+            "no_revision_available",
+            "",
+            "na",
+            "no-revision-available",
+        ]
+
+
+@pytest.mark.parametrize("model_rev_pair", model_rev_pairs)
+def test_organization_is_specified_for_new_additions(model_rev_pair):
+    """
+    Models added after 26th of November should include a organization ID within their name, e.g. "myorg/my_embedding_model".
+
+    This is to avoid mispecified names such as "myorg__my_embedding_model" and similar.
+    """
+    model_folder, rev_folder = model_rev_pair
+    meta_file = rev_folder / "model_meta.json"
+    with meta_file.open("r") as f:
+        meta = json.load(f)
+    assert "/" in meta["name"]