Update README.md
Browse files
README.md
CHANGED
@@ -13,4 +13,34 @@ language:
|
|
13 |
|
14 |
SOTA Open source french embedding model.
|
15 |
|
16 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
|
14 |
SOTA Open source french embedding model.
|
15 |
|
16 |
+
| Model | Mean Score |
|
17 |
+
| --- | --- |
|
18 |
+
| cohere/embed-multilingual-v3 | 0.7402 |
|
19 |
+
| OrdalieTech/Solon-embeddings-base-0.1 | 0.7306 |
|
20 |
+
| openai/ada-002 | 0.7290 |
|
21 |
+
| cohere/embed-multilingual-light-v3 | 0.6945 |
|
22 |
+
| antoinelouis/biencoder-camembert-base-mmarcoFR | 0.6826 |
|
23 |
+
| dangvantuan/sentence-camembert-large | 0.6756 |
|
24 |
+
| voyage/voyage-01 | 0.6753 |
|
25 |
+
| intfloat/multilingual-e5-large | 0.6660 |
|
26 |
+
| intfloat/multilingual-e5-base | 0.6597 |
|
27 |
+
| Sbert/paraphrase-multilingual-mpnet-base-v2 | 0.5975 |
|
28 |
+
| dangvantuan/sentence-camembert-base | 0.5456 |
|
29 |
+
| EuropeanParliament/eubert_embedding_v1 | 0.5063 |
|
30 |
+
|
31 |
+
These results have been obtained through 9 benchmarks on a variety of text similarity tasks (classification, reranking, STS) :
|
32 |
+
- AmazonReviewsClassification
|
33 |
+
- MassiveIntentClassification
|
34 |
+
- MassiveScenarioClassification
|
35 |
+
- MTOPDomainClassification
|
36 |
+
- MTOPIntentClassification
|
37 |
+
- STS22
|
38 |
+
- MiraclFRRerank
|
39 |
+
- OrdalieFRSTS
|
40 |
+
- OrdalieFRReranking
|
41 |
+
|
42 |
+
(evaluation script currently available here : github.com/netapy/mteb)
|
43 |
+
|
44 |
+
--------
|
45 |
+
|
46 |
+
(Large version comming soon)
|