Commit
•
d3f04e2
1
Parent(s):
f10c850
Adopt MTEB dataset naming scheme (#1)
Browse files- Adopt MTEB dataset naming scheme (d2ba7743ac656bd32d2622a969a65ea480d3f9d7)
Co-authored-by: Tom Aarsen <tomaarsen@users.noreply.huggingface.co>
README.md
CHANGED
@@ -4,7 +4,7 @@ model-index:
|
|
4 |
results:
|
5 |
- dataset:
|
6 |
config: default
|
7 |
-
name:
|
8 |
revision: c0ba03d058e3e1b2f3fd20518875a4563dd12db4
|
9 |
split: test
|
10 |
type: ai-forever/cedr-classification
|
@@ -21,7 +21,7 @@ model-index:
|
|
21 |
type: MultilabelClassification
|
22 |
- dataset:
|
23 |
config: default
|
24 |
-
name:
|
25 |
revision: 3765c0d1de6b7d264bc459433c45e5a75513839c
|
26 |
split: test
|
27 |
type: ai-forever/georeview-classification
|
@@ -38,7 +38,7 @@ model-index:
|
|
38 |
type: Classification
|
39 |
- dataset:
|
40 |
config: default
|
41 |
-
name:
|
42 |
revision: 97a313c8fc85b47f13f33e7e9a95c1ad888c7fec
|
43 |
split: test
|
44 |
type: ai-forever/georeview-clustering-p2p
|
@@ -53,7 +53,7 @@ model-index:
|
|
53 |
type: Clustering
|
54 |
- dataset:
|
55 |
config: default
|
56 |
-
name:
|
57 |
revision: 2fe05ee6b5832cda29f2ef7aaad7b7fe6a3609eb
|
58 |
split: test
|
59 |
type: ai-forever/headline-classification
|
@@ -70,7 +70,7 @@ model-index:
|
|
70 |
type: Classification
|
71 |
- dataset:
|
72 |
config: default
|
73 |
-
name:
|
74 |
revision: 601651fdc45ef243751676e62dd7a19f491c0285
|
75 |
split: test
|
76 |
type: ai-forever/inappropriateness-classification
|
@@ -91,7 +91,7 @@ model-index:
|
|
91 |
type: Classification
|
92 |
- dataset:
|
93 |
config: default
|
94 |
-
name:
|
95 |
revision: 5911f26666ac11af46cb9c6849d0dc80a378af24
|
96 |
split: test
|
97 |
type: ai-forever/kinopoisk-sentiment-classification
|
@@ -702,7 +702,7 @@ model-index:
|
|
702 |
type: Classification
|
703 |
- dataset:
|
704 |
config: default
|
705 |
-
name:
|
706 |
revision: 43265056790b8f7c59e0139acb4be0a8dad2c8f4
|
707 |
split: test
|
708 |
type: merionum/ru_paraphraser
|
@@ -729,7 +729,7 @@ model-index:
|
|
729 |
type: STS
|
730 |
- dataset:
|
731 |
config: default
|
732 |
-
name:
|
733 |
revision: 82374b0bbacda6114f39ff9c5b925fa1512ca5d7
|
734 |
split: test
|
735 |
type: ai-forever/ria-news-retrieval
|
@@ -1020,7 +1020,7 @@ model-index:
|
|
1020 |
type: Retrieval
|
1021 |
- dataset:
|
1022 |
config: default
|
1023 |
-
name:
|
1024 |
revision: 2e96b8f098fa4b0950fc58eacadeb31c0d0c7fa2
|
1025 |
split: test
|
1026 |
type: ai-forever/rubq-reranking
|
@@ -1047,7 +1047,7 @@ model-index:
|
|
1047 |
type: Reranking
|
1048 |
- dataset:
|
1049 |
config: default
|
1050 |
-
name:
|
1051 |
revision: e19b6ffa60b3bc248e0b41f4cc37c26a55c2a67b
|
1052 |
split: test
|
1053 |
type: ai-forever/rubq-retrieval
|
@@ -1338,7 +1338,7 @@ model-index:
|
|
1338 |
type: Retrieval
|
1339 |
- dataset:
|
1340 |
config: default
|
1341 |
-
name:
|
1342 |
revision: f6d2c31f4dc6b88f468552750bfec05b4b41b05a
|
1343 |
split: test
|
1344 |
type: ai-forever/ru-reviews-classification
|
@@ -1355,7 +1355,7 @@ model-index:
|
|
1355 |
type: Classification
|
1356 |
- dataset:
|
1357 |
config: default
|
1358 |
-
name:
|
1359 |
revision: 7cf24f325c6da6195df55bef3d86b5e0616f3018
|
1360 |
split: test
|
1361 |
type: ai-forever/ru-stsbenchmark-sts
|
@@ -1382,7 +1382,7 @@ model-index:
|
|
1382 |
type: STS
|
1383 |
- dataset:
|
1384 |
config: default
|
1385 |
-
name:
|
1386 |
revision: 673a610d6d3dd91a547a0d57ae1b56f37ebbf6a1
|
1387 |
split: test
|
1388 |
type: ai-forever/ru-scibench-grnti-classification
|
@@ -1399,7 +1399,7 @@ model-index:
|
|
1399 |
type: Classification
|
1400 |
- dataset:
|
1401 |
config: default
|
1402 |
-
name:
|
1403 |
revision: 673a610d6d3dd91a547a0d57ae1b56f37ebbf6a1
|
1404 |
split: test
|
1405 |
type: ai-forever/ru-scibench-grnti-classification
|
@@ -1414,7 +1414,7 @@ model-index:
|
|
1414 |
type: Clustering
|
1415 |
- dataset:
|
1416 |
config: default
|
1417 |
-
name:
|
1418 |
revision: 26c88e99dcaba32bb45d0e1bfc21902337f6d471
|
1419 |
split: test
|
1420 |
type: ai-forever/ru-scibench-oecd-classification
|
@@ -1431,7 +1431,7 @@ model-index:
|
|
1431 |
type: Classification
|
1432 |
- dataset:
|
1433 |
config: default
|
1434 |
-
name:
|
1435 |
revision: 26c88e99dcaba32bb45d0e1bfc21902337f6d471
|
1436 |
split: test
|
1437 |
type: ai-forever/ru-scibench-oecd-classification
|
@@ -1473,7 +1473,7 @@ model-index:
|
|
1473 |
type: STS
|
1474 |
- dataset:
|
1475 |
config: default
|
1476 |
-
name:
|
1477 |
revision: 416b34a802308eac30e4192afc0ff99bb8dcc7f2
|
1478 |
split: test
|
1479 |
type: ai-forever/sensitive-topics-classification
|
@@ -1490,7 +1490,7 @@ model-index:
|
|
1490 |
type: MultilabelClassification
|
1491 |
- dataset:
|
1492 |
config: default
|
1493 |
-
name:
|
1494 |
revision: 7b58f24536063837d644aab9a023c62199b2a612
|
1495 |
split: dev
|
1496 |
type: ai-forever/terra-pairclassification
|
@@ -1585,6 +1585,7 @@ tags:
|
|
1585 |
- mteb
|
1586 |
- transformers
|
1587 |
- sentence-transformers
|
|
|
1588 |
---
|
1589 |
|
1590 |
# Model Card for ru-en-RoSBERTa
|
|
|
4 |
results:
|
5 |
- dataset:
|
6 |
config: default
|
7 |
+
name: CEDRClassification (rus-Cyrl)
|
8 |
revision: c0ba03d058e3e1b2f3fd20518875a4563dd12db4
|
9 |
split: test
|
10 |
type: ai-forever/cedr-classification
|
|
|
21 |
type: MultilabelClassification
|
22 |
- dataset:
|
23 |
config: default
|
24 |
+
name: GeoreviewClassification (rus-Cyrl)
|
25 |
revision: 3765c0d1de6b7d264bc459433c45e5a75513839c
|
26 |
split: test
|
27 |
type: ai-forever/georeview-classification
|
|
|
38 |
type: Classification
|
39 |
- dataset:
|
40 |
config: default
|
41 |
+
name: GeoreviewClusteringP2P (rus-Cyrl)
|
42 |
revision: 97a313c8fc85b47f13f33e7e9a95c1ad888c7fec
|
43 |
split: test
|
44 |
type: ai-forever/georeview-clustering-p2p
|
|
|
53 |
type: Clustering
|
54 |
- dataset:
|
55 |
config: default
|
56 |
+
name: HeadlineClassification (rus-Cyrl)
|
57 |
revision: 2fe05ee6b5832cda29f2ef7aaad7b7fe6a3609eb
|
58 |
split: test
|
59 |
type: ai-forever/headline-classification
|
|
|
70 |
type: Classification
|
71 |
- dataset:
|
72 |
config: default
|
73 |
+
name: InappropriatenessClassification (rus-Cyrl)
|
74 |
revision: 601651fdc45ef243751676e62dd7a19f491c0285
|
75 |
split: test
|
76 |
type: ai-forever/inappropriateness-classification
|
|
|
91 |
type: Classification
|
92 |
- dataset:
|
93 |
config: default
|
94 |
+
name: KinopoiskClassification (rus-Cyrl)
|
95 |
revision: 5911f26666ac11af46cb9c6849d0dc80a378af24
|
96 |
split: test
|
97 |
type: ai-forever/kinopoisk-sentiment-classification
|
|
|
702 |
type: Classification
|
703 |
- dataset:
|
704 |
config: default
|
705 |
+
name: RUParaPhraserSTS (rus-Cyrl)
|
706 |
revision: 43265056790b8f7c59e0139acb4be0a8dad2c8f4
|
707 |
split: test
|
708 |
type: merionum/ru_paraphraser
|
|
|
729 |
type: STS
|
730 |
- dataset:
|
731 |
config: default
|
732 |
+
name: RiaNewsRetrieval (rus-Cyrl)
|
733 |
revision: 82374b0bbacda6114f39ff9c5b925fa1512ca5d7
|
734 |
split: test
|
735 |
type: ai-forever/ria-news-retrieval
|
|
|
1020 |
type: Retrieval
|
1021 |
- dataset:
|
1022 |
config: default
|
1023 |
+
name: RuBQReranking (rus-Cyrl)
|
1024 |
revision: 2e96b8f098fa4b0950fc58eacadeb31c0d0c7fa2
|
1025 |
split: test
|
1026 |
type: ai-forever/rubq-reranking
|
|
|
1047 |
type: Reranking
|
1048 |
- dataset:
|
1049 |
config: default
|
1050 |
+
name: RuBQRetrieval (rus-Cyrl)
|
1051 |
revision: e19b6ffa60b3bc248e0b41f4cc37c26a55c2a67b
|
1052 |
split: test
|
1053 |
type: ai-forever/rubq-retrieval
|
|
|
1338 |
type: Retrieval
|
1339 |
- dataset:
|
1340 |
config: default
|
1341 |
+
name: RuReviewsClassification (rus-Cyrl)
|
1342 |
revision: f6d2c31f4dc6b88f468552750bfec05b4b41b05a
|
1343 |
split: test
|
1344 |
type: ai-forever/ru-reviews-classification
|
|
|
1355 |
type: Classification
|
1356 |
- dataset:
|
1357 |
config: default
|
1358 |
+
name: RuSTSBenchmarkSTS (rus-Cyrl)
|
1359 |
revision: 7cf24f325c6da6195df55bef3d86b5e0616f3018
|
1360 |
split: test
|
1361 |
type: ai-forever/ru-stsbenchmark-sts
|
|
|
1382 |
type: STS
|
1383 |
- dataset:
|
1384 |
config: default
|
1385 |
+
name: RuSciBenchGRNTIClassification (rus-Cyrl)
|
1386 |
revision: 673a610d6d3dd91a547a0d57ae1b56f37ebbf6a1
|
1387 |
split: test
|
1388 |
type: ai-forever/ru-scibench-grnti-classification
|
|
|
1399 |
type: Classification
|
1400 |
- dataset:
|
1401 |
config: default
|
1402 |
+
name: RuSciBenchGRNTIClusteringP2P (rus-Cyrl)
|
1403 |
revision: 673a610d6d3dd91a547a0d57ae1b56f37ebbf6a1
|
1404 |
split: test
|
1405 |
type: ai-forever/ru-scibench-grnti-classification
|
|
|
1414 |
type: Clustering
|
1415 |
- dataset:
|
1416 |
config: default
|
1417 |
+
name: RuSciBenchOECDClassification (rus-Cyrl)
|
1418 |
revision: 26c88e99dcaba32bb45d0e1bfc21902337f6d471
|
1419 |
split: test
|
1420 |
type: ai-forever/ru-scibench-oecd-classification
|
|
|
1431 |
type: Classification
|
1432 |
- dataset:
|
1433 |
config: default
|
1434 |
+
name: RuSciBenchOECDClusteringP2P (rus-Cyrl)
|
1435 |
revision: 26c88e99dcaba32bb45d0e1bfc21902337f6d471
|
1436 |
split: test
|
1437 |
type: ai-forever/ru-scibench-oecd-classification
|
|
|
1473 |
type: STS
|
1474 |
- dataset:
|
1475 |
config: default
|
1476 |
+
name: SensitiveTopicsClassification (rus-Cyrl)
|
1477 |
revision: 416b34a802308eac30e4192afc0ff99bb8dcc7f2
|
1478 |
split: test
|
1479 |
type: ai-forever/sensitive-topics-classification
|
|
|
1490 |
type: MultilabelClassification
|
1491 |
- dataset:
|
1492 |
config: default
|
1493 |
+
name: TERRa (rus-Cyrl)
|
1494 |
revision: 7b58f24536063837d644aab9a023c62199b2a612
|
1495 |
split: dev
|
1496 |
type: ai-forever/terra-pairclassification
|
|
|
1585 |
- mteb
|
1586 |
- transformers
|
1587 |
- sentence-transformers
|
1588 |
+
base_model: ai-forever/ruRoberta-large
|
1589 |
---
|
1590 |
|
1591 |
# Model Card for ru-en-RoSBERTa
|