Update README.md
Browse files
README.md
CHANGED
@@ -6,19 +6,1528 @@ tags:
|
|
6 |
- feature-extraction
|
7 |
- sentence-similarity
|
8 |
- transformers
|
9 |
-
- phobert
|
10 |
- french
|
|
|
11 |
- sentence-embedding
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
license: apache-2.0
|
13 |
language:
|
14 |
- fr
|
15 |
- en
|
16 |
-
metrics:
|
17 |
-
- pearsonr
|
18 |
-
- spearmanr
|
19 |
---
|
20 |
## Model Description:
|
21 |
-
[**french-embedding
|
22 |
|
23 |
## Full Model Architecture
|
24 |
```
|
@@ -28,14 +1537,6 @@ SentenceTransformer(
|
|
28 |
(2): Normalize()
|
29 |
)
|
30 |
```
|
31 |
-
## Training and Fine-tuning process
|
32 |
-
The model underwent a rigorous four-stage training and fine-tuning process, each tailored to enhance its ability to generate precise and contextually relevant sentence embeddings for the french language. Below is an outline of these stages:
|
33 |
-
#### Stage 1: Training NLI on dataset XNLI:
|
34 |
-
- Dataset: XNLI (fr-en)
|
35 |
-
- Method: Training using Multi-Negative Ranking Loss and Matryoshka2dLoss. This stage focused on improving the model's ability to discern and rank nuanced differences in sentence semantics.
|
36 |
-
### Stage 2: Fine-tuning for Semantic Textual Similarity on STS Benchmark
|
37 |
-
- Dataset: STS-B (fr-en)
|
38 |
-
- Method: Fine-tuning specifically for the semantic textual similarity benchmark using Siamese BERT-Networks configured with the 'sentence-transformers' library. This stage honed the model's precision in capturing semantic similarity across various types of french texts.
|
39 |
|
40 |
|
41 |
## Usage:
|
@@ -54,7 +1555,7 @@ sentences = ["Paris est une capitale de la France", "Paris is a capital of Franc
|
|
54 |
|
55 |
|
56 |
|
57 |
-
model = SentenceTransformer('dangvantuan/french-embedding
|
58 |
embeddings = model.encode(sentences)
|
59 |
print(embeddings)
|
60 |
|
@@ -78,7 +1579,6 @@ print(embeddings)
|
|
78 |
year={2019}
|
79 |
}
|
80 |
|
81 |
-
|
82 |
@article{zhang2024mgte,
|
83 |
title={mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval},
|
84 |
author={Zhang, Xin and Zhang, Yanzhao and Long, Dingkun and Xie, Wen and Dai, Ziqi and Tang, Jialong and Lin, Huan and Yang, Baosong and Xie, Pengjun and Huang, Fei and others},
|
@@ -98,4 +1598,22 @@ print(embeddings)
|
|
98 |
author={Li, Xianming and Li, Zongxi and Li, Jing and Xie, Haoran and Li, Qing},
|
99 |
journal={arXiv preprint arXiv:2402.14776},
|
100 |
year={2024}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
101 |
}
|
|
|
6 |
- feature-extraction
|
7 |
- sentence-similarity
|
8 |
- transformers
|
|
|
9 |
- french
|
10 |
+
- english
|
11 |
- sentence-embedding
|
12 |
+
- mteb
|
13 |
+
model-index:
|
14 |
+
- name: 7eff199d41ff669fad99d83cad9249c393c3f14b
|
15 |
+
results:
|
16 |
+
- task:
|
17 |
+
type: Clustering
|
18 |
+
dataset:
|
19 |
+
type: lyon-nlp/alloprof
|
20 |
+
name: MTEB AlloProfClusteringP2P
|
21 |
+
config: default
|
22 |
+
split: test
|
23 |
+
revision: 392ba3f5bcc8c51f578786c1fc3dae648662cb9b
|
24 |
+
metrics:
|
25 |
+
- type: v_measure
|
26 |
+
value: 59.69196295449414
|
27 |
+
- type: v_measures
|
28 |
+
value: [0.6355772777559684, 0.4980707615440343, 0.5851538838323186, 0.6567709175938427, 0.5712405288636999]
|
29 |
+
- task:
|
30 |
+
type: Clustering
|
31 |
+
dataset:
|
32 |
+
type: lyon-nlp/alloprof
|
33 |
+
name: MTEB AlloProfClusteringS2S
|
34 |
+
config: default
|
35 |
+
split: test
|
36 |
+
revision: 392ba3f5bcc8c51f578786c1fc3dae648662cb9b
|
37 |
+
metrics:
|
38 |
+
- type: v_measure
|
39 |
+
value: 45.607106996926426
|
40 |
+
- type: v_measures
|
41 |
+
value: [0.45846869913649535, 0.42657120373128293, 0.45507356125930876, 0.4258913306353704, 0.4779122207000794]
|
42 |
+
- task:
|
43 |
+
type: Reranking
|
44 |
+
dataset:
|
45 |
+
type: lyon-nlp/mteb-fr-reranking-alloprof-s2p
|
46 |
+
name: MTEB AlloprofReranking
|
47 |
+
config: default
|
48 |
+
split: test
|
49 |
+
revision: 65393d0d7a08a10b4e348135e824f385d420b0fd
|
50 |
+
metrics:
|
51 |
+
- type: map
|
52 |
+
value: 73.51836428087765
|
53 |
+
- type: mrr
|
54 |
+
value: 74.8550285111166
|
55 |
+
- type: nAUC_map_diff1
|
56 |
+
value: 56.006169898728466
|
57 |
+
- type: nAUC_map_max
|
58 |
+
value: 27.886037223407506
|
59 |
+
- type: nAUC_mrr_diff1
|
60 |
+
value: 56.68072778248672
|
61 |
+
- type: nAUC_mrr_max
|
62 |
+
value: 29.362681962243276
|
63 |
+
- task:
|
64 |
+
type: Retrieval
|
65 |
+
dataset:
|
66 |
+
type: lyon-nlp/alloprof
|
67 |
+
name: MTEB AlloprofRetrieval
|
68 |
+
config: default
|
69 |
+
split: test
|
70 |
+
revision: fcf295ea64c750f41fadbaa37b9b861558e1bfbd
|
71 |
+
metrics:
|
72 |
+
- type: map_at_1
|
73 |
+
value: 32.080999999999996
|
74 |
+
- type: map_at_10
|
75 |
+
value: 43.582
|
76 |
+
- type: map_at_100
|
77 |
+
value: 44.381
|
78 |
+
- type: map_at_1000
|
79 |
+
value: 44.426
|
80 |
+
- type: map_at_20
|
81 |
+
value: 44.061
|
82 |
+
- type: map_at_3
|
83 |
+
value: 40.602
|
84 |
+
- type: map_at_5
|
85 |
+
value: 42.381
|
86 |
+
- type: mrr_at_1
|
87 |
+
value: 32.08117443868739
|
88 |
+
- type: mrr_at_10
|
89 |
+
value: 43.5823429832498
|
90 |
+
- type: mrr_at_100
|
91 |
+
value: 44.38068560877513
|
92 |
+
- type: mrr_at_1000
|
93 |
+
value: 44.426194305504026
|
94 |
+
- type: mrr_at_20
|
95 |
+
value: 44.06128094655753
|
96 |
+
- type: mrr_at_3
|
97 |
+
value: 40.60161197466903
|
98 |
+
- type: mrr_at_5
|
99 |
+
value: 42.380541162924715
|
100 |
+
- type: nauc_map_at_1000_diff1
|
101 |
+
value: 37.22997629352391
|
102 |
+
- type: nauc_map_at_1000_max
|
103 |
+
value: 38.65090969900466
|
104 |
+
- type: nauc_map_at_100_diff1
|
105 |
+
value: 37.22644507166512
|
106 |
+
- type: nauc_map_at_100_max
|
107 |
+
value: 38.67447923917633
|
108 |
+
- type: nauc_map_at_10_diff1
|
109 |
+
value: 37.02440573022942
|
110 |
+
- type: nauc_map_at_10_max
|
111 |
+
value: 38.52972171430789
|
112 |
+
- type: nauc_map_at_1_diff1
|
113 |
+
value: 41.18101653444774
|
114 |
+
- type: nauc_map_at_1_max
|
115 |
+
value: 34.87383192583458
|
116 |
+
- type: nauc_map_at_20_diff1
|
117 |
+
value: 37.14172285932024
|
118 |
+
- type: nauc_map_at_20_max
|
119 |
+
value: 38.66753159239803
|
120 |
+
- type: nauc_map_at_3_diff1
|
121 |
+
value: 37.53556306862998
|
122 |
+
- type: nauc_map_at_3_max
|
123 |
+
value: 37.86008195327724
|
124 |
+
- type: nauc_map_at_5_diff1
|
125 |
+
value: 37.14904081229067
|
126 |
+
- type: nauc_map_at_5_max
|
127 |
+
value: 38.267819714061105
|
128 |
+
- type: nauc_mrr_at_1000_diff1
|
129 |
+
value: 37.22997629352391
|
130 |
+
- type: nauc_mrr_at_1000_max
|
131 |
+
value: 38.65090969900466
|
132 |
+
- type: nauc_mrr_at_100_diff1
|
133 |
+
value: 37.22644507166512
|
134 |
+
- type: nauc_mrr_at_100_max
|
135 |
+
value: 38.67447923917633
|
136 |
+
- type: nauc_mrr_at_10_diff1
|
137 |
+
value: 37.02440573022942
|
138 |
+
- type: nauc_mrr_at_10_max
|
139 |
+
value: 38.52972171430789
|
140 |
+
- type: nauc_mrr_at_1_diff1
|
141 |
+
value: 41.18101653444774
|
142 |
+
- type: nauc_mrr_at_1_max
|
143 |
+
value: 34.87383192583458
|
144 |
+
- type: nauc_mrr_at_20_diff1
|
145 |
+
value: 37.14172285932024
|
146 |
+
- type: nauc_mrr_at_20_max
|
147 |
+
value: 38.66753159239803
|
148 |
+
- type: nauc_mrr_at_3_diff1
|
149 |
+
value: 37.53556306862998
|
150 |
+
- type: nauc_mrr_at_3_max
|
151 |
+
value: 37.86008195327724
|
152 |
+
- type: nauc_mrr_at_5_diff1
|
153 |
+
value: 37.14904081229067
|
154 |
+
- type: nauc_mrr_at_5_max
|
155 |
+
value: 38.267819714061105
|
156 |
+
- type: nauc_ndcg_at_1000_diff1
|
157 |
+
value: 36.313082263552204
|
158 |
+
- type: nauc_ndcg_at_1000_max
|
159 |
+
value: 40.244406213773765
|
160 |
+
- type: nauc_ndcg_at_100_diff1
|
161 |
+
value: 36.17060946689135
|
162 |
+
- type: nauc_ndcg_at_100_max
|
163 |
+
value: 41.069278488584416
|
164 |
+
- type: nauc_ndcg_at_10_diff1
|
165 |
+
value: 35.2775471480974
|
166 |
+
- type: nauc_ndcg_at_10_max
|
167 |
+
value: 40.33902753007036
|
168 |
+
- type: nauc_ndcg_at_1_diff1
|
169 |
+
value: 41.18101653444774
|
170 |
+
- type: nauc_ndcg_at_1_max
|
171 |
+
value: 34.87383192583458
|
172 |
+
- type: nauc_ndcg_at_20_diff1
|
173 |
+
value: 35.71067272175871
|
174 |
+
- type: nauc_ndcg_at_20_max
|
175 |
+
value: 40.94374381572908
|
176 |
+
- type: nauc_ndcg_at_3_diff1
|
177 |
+
value: 36.45082651868188
|
178 |
+
- type: nauc_ndcg_at_3_max
|
179 |
+
value: 38.87195110158222
|
180 |
+
- type: nauc_ndcg_at_5_diff1
|
181 |
+
value: 35.683568481780505
|
182 |
+
- type: nauc_ndcg_at_5_max
|
183 |
+
value: 39.606933866599
|
184 |
+
- type: nauc_precision_at_1000_diff1
|
185 |
+
value: 15.489726515767439
|
186 |
+
- type: nauc_precision_at_1000_max
|
187 |
+
value: 75.94259161180715
|
188 |
+
- type: nauc_precision_at_100_diff1
|
189 |
+
value: 30.033605095284656
|
190 |
+
- type: nauc_precision_at_100_max
|
191 |
+
value: 62.40786465750442
|
192 |
+
- type: nauc_precision_at_10_diff1
|
193 |
+
value: 28.617170969915
|
194 |
+
- type: nauc_precision_at_10_max
|
195 |
+
value: 47.35884745487521
|
196 |
+
- type: nauc_precision_at_1_diff1
|
197 |
+
value: 41.18101653444774
|
198 |
+
- type: nauc_precision_at_1_max
|
199 |
+
value: 34.87383192583458
|
200 |
+
- type: nauc_precision_at_20_diff1
|
201 |
+
value: 29.730952749557144
|
202 |
+
- type: nauc_precision_at_20_max
|
203 |
+
value: 52.09696741873719
|
204 |
+
- type: nauc_precision_at_3_diff1
|
205 |
+
value: 33.30844921569695
|
206 |
+
- type: nauc_precision_at_3_max
|
207 |
+
value: 41.84496633792437
|
208 |
+
- type: nauc_precision_at_5_diff1
|
209 |
+
value: 31.000246292430838
|
210 |
+
- type: nauc_precision_at_5_max
|
211 |
+
value: 43.88721507465343
|
212 |
+
- type: nauc_recall_at_1000_diff1
|
213 |
+
value: 15.48972651576705
|
214 |
+
- type: nauc_recall_at_1000_max
|
215 |
+
value: 75.94259161180725
|
216 |
+
- type: nauc_recall_at_100_diff1
|
217 |
+
value: 30.033605095284816
|
218 |
+
- type: nauc_recall_at_100_max
|
219 |
+
value: 62.40786465750426
|
220 |
+
- type: nauc_recall_at_10_diff1
|
221 |
+
value: 28.617170969914984
|
222 |
+
- type: nauc_recall_at_10_max
|
223 |
+
value: 47.35884745487525
|
224 |
+
- type: nauc_recall_at_1_diff1
|
225 |
+
value: 41.18101653444774
|
226 |
+
- type: nauc_recall_at_1_max
|
227 |
+
value: 34.87383192583458
|
228 |
+
- type: nauc_recall_at_20_diff1
|
229 |
+
value: 29.730952749557087
|
230 |
+
- type: nauc_recall_at_20_max
|
231 |
+
value: 52.09696741873715
|
232 |
+
- type: nauc_recall_at_3_diff1
|
233 |
+
value: 33.30844921569694
|
234 |
+
- type: nauc_recall_at_3_max
|
235 |
+
value: 41.84496633792433
|
236 |
+
- type: nauc_recall_at_5_diff1
|
237 |
+
value: 31.000246292430838
|
238 |
+
- type: nauc_recall_at_5_max
|
239 |
+
value: 43.88721507465339
|
240 |
+
- type: ndcg_at_1
|
241 |
+
value: 32.080999999999996
|
242 |
+
- type: ndcg_at_10
|
243 |
+
value: 49.502
|
244 |
+
- type: ndcg_at_100
|
245 |
+
value: 53.52
|
246 |
+
- type: ndcg_at_1000
|
247 |
+
value: 54.842
|
248 |
+
- type: ndcg_at_20
|
249 |
+
value: 51.219
|
250 |
+
- type: ndcg_at_3
|
251 |
+
value: 43.381
|
252 |
+
- type: ndcg_at_5
|
253 |
+
value: 46.603
|
254 |
+
- type: precision_at_1
|
255 |
+
value: 32.080999999999996
|
256 |
+
- type: precision_at_10
|
257 |
+
value: 6.822
|
258 |
+
- type: precision_at_100
|
259 |
+
value: 0.873
|
260 |
+
- type: precision_at_1000
|
261 |
+
value: 0.098
|
262 |
+
- type: precision_at_20
|
263 |
+
value: 3.7479999999999998
|
264 |
+
- type: precision_at_3
|
265 |
+
value: 17.142
|
266 |
+
- type: precision_at_5
|
267 |
+
value: 11.857
|
268 |
+
- type: recall_at_1
|
269 |
+
value: 32.080999999999996
|
270 |
+
- type: recall_at_10
|
271 |
+
value: 68.221
|
272 |
+
- type: recall_at_100
|
273 |
+
value: 87.349
|
274 |
+
- type: recall_at_1000
|
275 |
+
value: 98.014
|
276 |
+
- type: recall_at_20
|
277 |
+
value: 74.957
|
278 |
+
- type: recall_at_3
|
279 |
+
value: 51.425
|
280 |
+
- type: recall_at_5
|
281 |
+
value: 59.282999999999994
|
282 |
+
- task:
|
283 |
+
type: Classification
|
284 |
+
dataset:
|
285 |
+
type: mteb/amazon_reviews_multi
|
286 |
+
name: MTEB AmazonReviewsClassification (fr)
|
287 |
+
config: fr
|
288 |
+
split: test
|
289 |
+
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
|
290 |
+
metrics:
|
291 |
+
- type: accuracy
|
292 |
+
value: 39.892
|
293 |
+
- type: f1
|
294 |
+
value: 38.38126304364462
|
295 |
+
- type: f1_weighted
|
296 |
+
value: 38.38126304364462
|
297 |
+
- task:
|
298 |
+
type: Retrieval
|
299 |
+
dataset:
|
300 |
+
type: maastrichtlawtech/bsard
|
301 |
+
name: MTEB BSARDRetrieval
|
302 |
+
config: default
|
303 |
+
split: test
|
304 |
+
revision: 5effa1b9b5fa3b0f9e12523e6e43e5f86a6e6d59
|
305 |
+
metrics:
|
306 |
+
- type: map_at_1
|
307 |
+
value: 10.811
|
308 |
+
- type: map_at_10
|
309 |
+
value: 16.414
|
310 |
+
- type: map_at_100
|
311 |
+
value: 17.647
|
312 |
+
- type: map_at_1000
|
313 |
+
value: 17.742
|
314 |
+
- type: map_at_20
|
315 |
+
value: 17.22
|
316 |
+
- type: map_at_3
|
317 |
+
value: 14.188999999999998
|
318 |
+
- type: map_at_5
|
319 |
+
value: 15.113
|
320 |
+
- type: mrr_at_1
|
321 |
+
value: 10.81081081081081
|
322 |
+
- type: mrr_at_10
|
323 |
+
value: 16.41427141427142
|
324 |
+
- type: mrr_at_100
|
325 |
+
value: 17.647339314041712
|
326 |
+
- type: mrr_at_1000
|
327 |
+
value: 17.74213263983212
|
328 |
+
- type: mrr_at_20
|
329 |
+
value: 17.219989884463573
|
330 |
+
- type: mrr_at_3
|
331 |
+
value: 14.18918918918919
|
332 |
+
- type: mrr_at_5
|
333 |
+
value: 15.112612612612612
|
334 |
+
- type: nauc_map_at_1000_diff1
|
335 |
+
value: 13.07108195916555
|
336 |
+
- type: nauc_map_at_1000_max
|
337 |
+
value: 14.000521014179807
|
338 |
+
- type: nauc_map_at_100_diff1
|
339 |
+
value: 13.087117094079332
|
340 |
+
- type: nauc_map_at_100_max
|
341 |
+
value: 13.99712558752583
|
342 |
+
- type: nauc_map_at_10_diff1
|
343 |
+
value: 13.452029501381165
|
344 |
+
- type: nauc_map_at_10_max
|
345 |
+
value: 13.3341655571542
|
346 |
+
- type: nauc_map_at_1_diff1
|
347 |
+
value: 14.990419981155167
|
348 |
+
- type: nauc_map_at_1_max
|
349 |
+
value: 8.812519082504037
|
350 |
+
- type: nauc_map_at_20_diff1
|
351 |
+
value: 12.80321357992737
|
352 |
+
- type: nauc_map_at_20_max
|
353 |
+
value: 14.020962859032371
|
354 |
+
- type: nauc_map_at_3_diff1
|
355 |
+
value: 14.84230805712973
|
356 |
+
- type: nauc_map_at_3_max
|
357 |
+
value: 11.644032755353722
|
358 |
+
- type: nauc_map_at_5_diff1
|
359 |
+
value: 15.100168959732835
|
360 |
+
- type: nauc_map_at_5_max
|
361 |
+
value: 13.634801099074355
|
362 |
+
- type: nauc_mrr_at_1000_diff1
|
363 |
+
value: 13.07108195916555
|
364 |
+
- type: nauc_mrr_at_1000_max
|
365 |
+
value: 14.000521014179807
|
366 |
+
- type: nauc_mrr_at_100_diff1
|
367 |
+
value: 13.087117094079332
|
368 |
+
- type: nauc_mrr_at_100_max
|
369 |
+
value: 13.99712558752583
|
370 |
+
- type: nauc_mrr_at_10_diff1
|
371 |
+
value: 13.452029501381165
|
372 |
+
- type: nauc_mrr_at_10_max
|
373 |
+
value: 13.3341655571542
|
374 |
+
- type: nauc_mrr_at_1_diff1
|
375 |
+
value: 14.990419981155167
|
376 |
+
- type: nauc_mrr_at_1_max
|
377 |
+
value: 8.812519082504037
|
378 |
+
- type: nauc_mrr_at_20_diff1
|
379 |
+
value: 12.80321357992737
|
380 |
+
- type: nauc_mrr_at_20_max
|
381 |
+
value: 14.020962859032371
|
382 |
+
- type: nauc_mrr_at_3_diff1
|
383 |
+
value: 14.84230805712973
|
384 |
+
- type: nauc_mrr_at_3_max
|
385 |
+
value: 11.644032755353722
|
386 |
+
- type: nauc_mrr_at_5_diff1
|
387 |
+
value: 15.100168959732835
|
388 |
+
- type: nauc_mrr_at_5_max
|
389 |
+
value: 13.634801099074355
|
390 |
+
- type: nauc_ndcg_at_1000_diff1
|
391 |
+
value: 11.335350893370972
|
392 |
+
- type: nauc_ndcg_at_1000_max
|
393 |
+
value: 16.09665875369169
|
394 |
+
- type: nauc_ndcg_at_100_diff1
|
395 |
+
value: 11.499643600969176
|
396 |
+
- type: nauc_ndcg_at_100_max
|
397 |
+
value: 15.967105414704186
|
398 |
+
- type: nauc_ndcg_at_10_diff1
|
399 |
+
value: 12.093263549786606
|
400 |
+
- type: nauc_ndcg_at_10_max
|
401 |
+
value: 14.605821897766461
|
402 |
+
- type: nauc_ndcg_at_1_diff1
|
403 |
+
value: 14.990419981155167
|
404 |
+
- type: nauc_ndcg_at_1_max
|
405 |
+
value: 8.812519082504037
|
406 |
+
- type: nauc_ndcg_at_20_diff1
|
407 |
+
value: 10.197380043193812
|
408 |
+
- type: nauc_ndcg_at_20_max
|
409 |
+
value: 16.332533239525365
|
410 |
+
- type: nauc_ndcg_at_3_diff1
|
411 |
+
value: 14.835825175950765
|
412 |
+
- type: nauc_ndcg_at_3_max
|
413 |
+
value: 11.898757954417214
|
414 |
+
- type: nauc_ndcg_at_5_diff1
|
415 |
+
value: 15.278603386081823
|
416 |
+
- type: nauc_ndcg_at_5_max
|
417 |
+
value: 15.007133861218167
|
418 |
+
- type: nauc_precision_at_1000_diff1
|
419 |
+
value: 2.7469897420865195
|
420 |
+
- type: nauc_precision_at_1000_max
|
421 |
+
value: 26.874535278616346
|
422 |
+
- type: nauc_precision_at_100_diff1
|
423 |
+
value: 7.600735526139776
|
424 |
+
- type: nauc_precision_at_100_max
|
425 |
+
value: 20.7203382946415
|
426 |
+
- type: nauc_precision_at_10_diff1
|
427 |
+
value: 8.938642089366768
|
428 |
+
- type: nauc_precision_at_10_max
|
429 |
+
value: 17.320961743140874
|
430 |
+
- type: nauc_precision_at_1_diff1
|
431 |
+
value: 14.990419981155167
|
432 |
+
- type: nauc_precision_at_1_max
|
433 |
+
value: 8.812519082504037
|
434 |
+
- type: nauc_precision_at_20_diff1
|
435 |
+
value: 3.733877816322278
|
436 |
+
- type: nauc_precision_at_20_max
|
437 |
+
value: 21.581173305923002
|
438 |
+
- type: nauc_precision_at_3_diff1
|
439 |
+
value: 14.828850401790316
|
440 |
+
- type: nauc_precision_at_3_max
|
441 |
+
value: 12.369943286612463
|
442 |
+
- type: nauc_precision_at_5_diff1
|
443 |
+
value: 15.728617939150672
|
444 |
+
- type: nauc_precision_at_5_max
|
445 |
+
value: 18.103783411900697
|
446 |
+
- type: nauc_recall_at_1000_diff1
|
447 |
+
value: 2.746989742086615
|
448 |
+
- type: nauc_recall_at_1000_max
|
449 |
+
value: 26.874535278616367
|
450 |
+
- type: nauc_recall_at_100_diff1
|
451 |
+
value: 7.600735526139775
|
452 |
+
- type: nauc_recall_at_100_max
|
453 |
+
value: 20.720338294641536
|
454 |
+
- type: nauc_recall_at_10_diff1
|
455 |
+
value: 8.93864208936673
|
456 |
+
- type: nauc_recall_at_10_max
|
457 |
+
value: 17.32096174314083
|
458 |
+
- type: nauc_recall_at_1_diff1
|
459 |
+
value: 14.990419981155167
|
460 |
+
- type: nauc_recall_at_1_max
|
461 |
+
value: 8.812519082504037
|
462 |
+
- type: nauc_recall_at_20_diff1
|
463 |
+
value: 3.733877816322231
|
464 |
+
- type: nauc_recall_at_20_max
|
465 |
+
value: 21.58117330592295
|
466 |
+
- type: nauc_recall_at_3_diff1
|
467 |
+
value: 14.828850401790339
|
468 |
+
- type: nauc_recall_at_3_max
|
469 |
+
value: 12.369943286612509
|
470 |
+
- type: nauc_recall_at_5_diff1
|
471 |
+
value: 15.72861793915063
|
472 |
+
- type: nauc_recall_at_5_max
|
473 |
+
value: 18.103783411900658
|
474 |
+
- type: ndcg_at_1
|
475 |
+
value: 10.811
|
476 |
+
- type: ndcg_at_10
|
477 |
+
value: 20.244
|
478 |
+
- type: ndcg_at_100
|
479 |
+
value: 26.526
|
480 |
+
- type: ndcg_at_1000
|
481 |
+
value: 29.217
|
482 |
+
- type: ndcg_at_20
|
483 |
+
value: 23.122
|
484 |
+
- type: ndcg_at_3
|
485 |
+
value: 15.396
|
486 |
+
- type: ndcg_at_5
|
487 |
+
value: 17.063
|
488 |
+
- type: precision_at_1
|
489 |
+
value: 10.811
|
490 |
+
- type: precision_at_10
|
491 |
+
value: 3.288
|
492 |
+
- type: precision_at_100
|
493 |
+
value: 0.631
|
494 |
+
- type: precision_at_1000
|
495 |
+
value: 0.08499999999999999
|
496 |
+
- type: precision_at_20
|
497 |
+
value: 2.207
|
498 |
+
- type: precision_at_3
|
499 |
+
value: 6.306000000000001
|
500 |
+
- type: precision_at_5
|
501 |
+
value: 4.595
|
502 |
+
- type: recall_at_1
|
503 |
+
value: 10.811
|
504 |
+
- type: recall_at_10
|
505 |
+
value: 32.883
|
506 |
+
- type: recall_at_100
|
507 |
+
value: 63.063
|
508 |
+
- type: recall_at_1000
|
509 |
+
value: 84.685
|
510 |
+
- type: recall_at_20
|
511 |
+
value: 44.144
|
512 |
+
- type: recall_at_3
|
513 |
+
value: 18.919
|
514 |
+
- type: recall_at_5
|
515 |
+
value: 22.973
|
516 |
+
- task:
|
517 |
+
type: Clustering
|
518 |
+
dataset:
|
519 |
+
type: lyon-nlp/clustering-hal-s2s
|
520 |
+
name: MTEB HALClusteringS2S
|
521 |
+
config: default
|
522 |
+
split: test
|
523 |
+
revision: e06ebbbb123f8144bef1a5d18796f3dec9ae2915
|
524 |
+
metrics:
|
525 |
+
- type: v_measure
|
526 |
+
value: 25.209561281028435
|
527 |
+
- type: v_measures
|
528 |
+
value: [0.28558356565178666, 0.2707322246129254, 0.2683693125038299, 0.2703937853835602, 0.22057190525667872]
|
529 |
+
- task:
|
530 |
+
type: Clustering
|
531 |
+
dataset:
|
532 |
+
type: reciTAL/mlsum
|
533 |
+
name: MTEB MLSUMClusteringP2P
|
534 |
+
config: default
|
535 |
+
split: test
|
536 |
+
revision: b5d54f8f3b61ae17845046286940f03c6bc79bc7
|
537 |
+
metrics:
|
538 |
+
- type: v_measure
|
539 |
+
value: 42.82528809996964
|
540 |
+
- type: v_measures
|
541 |
+
value: [0.43465029372260205, 0.42821098223656917, 0.43537879149583325, 0.4289578694928627, 0.3794307754465835]
|
542 |
+
- task:
|
543 |
+
type: Clustering
|
544 |
+
dataset:
|
545 |
+
type: reciTAL/mlsum
|
546 |
+
name: MTEB MLSUMClusteringS2S
|
547 |
+
config: default
|
548 |
+
split: test
|
549 |
+
revision: b5d54f8f3b61ae17845046286940f03c6bc79bc7
|
550 |
+
metrics:
|
551 |
+
- type: v_measure
|
552 |
+
value: 43.44172295073941
|
553 |
+
- type: v_measures
|
554 |
+
value: [0.4294163918345751, 0.46229994906725164, 0.44188446196569603, 0.43839320352264155, 0.3866853445120933]
|
555 |
+
- task:
|
556 |
+
type: Classification
|
557 |
+
dataset:
|
558 |
+
type: mteb/mtop_domain
|
559 |
+
name: MTEB MTOPDomainClassification (fr)
|
560 |
+
config: fr
|
561 |
+
split: test
|
562 |
+
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
|
563 |
+
metrics:
|
564 |
+
- type: accuracy
|
565 |
+
value: 88.33072345756342
|
566 |
+
- type: f1
|
567 |
+
value: 88.11780476022122
|
568 |
+
- type: f1_weighted
|
569 |
+
value: 88.28188145087299
|
570 |
+
- task:
|
571 |
+
type: Classification
|
572 |
+
dataset:
|
573 |
+
type: mteb/mtop_intent
|
574 |
+
name: MTEB MTOPIntentClassification (fr)
|
575 |
+
config: fr
|
576 |
+
split: test
|
577 |
+
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
|
578 |
+
metrics:
|
579 |
+
- type: accuracy
|
580 |
+
value: 57.854682117131226
|
581 |
+
- type: f1
|
582 |
+
value: 41.121569078191996
|
583 |
+
- type: f1_weighted
|
584 |
+
value: 60.04845437480532
|
585 |
+
- task:
|
586 |
+
type: Classification
|
587 |
+
dataset:
|
588 |
+
type: mteb/masakhanews
|
589 |
+
name: MTEB MasakhaNEWSClassification (fra)
|
590 |
+
config: fra
|
591 |
+
split: test
|
592 |
+
revision: 18193f187b92da67168c655c9973a165ed9593dd
|
593 |
+
metrics:
|
594 |
+
- type: accuracy
|
595 |
+
value: 76.87203791469194
|
596 |
+
- type: f1
|
597 |
+
value: 72.94847557303437
|
598 |
+
- type: f1_weighted
|
599 |
+
value: 76.9128173959562
|
600 |
+
- task:
|
601 |
+
type: Clustering
|
602 |
+
dataset:
|
603 |
+
type: masakhane/masakhanews
|
604 |
+
name: MTEB MasakhaNEWSClusteringP2P (fra)
|
605 |
+
config: fra
|
606 |
+
split: test
|
607 |
+
revision: 8ccc72e69e65f40c70e117d8b3c08306bb788b60
|
608 |
+
metrics:
|
609 |
+
- type: v_measure
|
610 |
+
value: 61.32006896333715
|
611 |
+
- type: v_measures
|
612 |
+
value: [1.0, 0.6446188396257355, 0.28995363026757603, 0.40898735994696084, 0.7224436183265853]
|
613 |
+
- task:
|
614 |
+
type: Clustering
|
615 |
+
dataset:
|
616 |
+
type: masakhane/masakhanews
|
617 |
+
name: MTEB MasakhaNEWSClusteringS2S (fra)
|
618 |
+
config: fra
|
619 |
+
split: test
|
620 |
+
revision: 8ccc72e69e65f40c70e117d8b3c08306bb788b60
|
621 |
+
metrics:
|
622 |
+
- type: v_measure
|
623 |
+
value: 60.509887123660256
|
624 |
+
- type: v_measures
|
625 |
+
value: [1.0, 0.022472587992562534, 0.4686320087689936, 0.811946141094871, 0.7224436183265853]
|
626 |
+
- task:
|
627 |
+
type: Classification
|
628 |
+
dataset:
|
629 |
+
type: mteb/amazon_massive_intent
|
630 |
+
name: MTEB MassiveIntentClassification (fr)
|
631 |
+
config: fr
|
632 |
+
split: test
|
633 |
+
revision: 4672e20407010da34463acc759c162ca9734bca6
|
634 |
+
metrics:
|
635 |
+
- type: accuracy
|
636 |
+
value: 64.14256893073302
|
637 |
+
- type: f1
|
638 |
+
value: 61.33068109342782
|
639 |
+
- type: f1_weighted
|
640 |
+
value: 62.74292948992287
|
641 |
+
- task:
|
642 |
+
type: Classification
|
643 |
+
dataset:
|
644 |
+
type: mteb/amazon_massive_scenario
|
645 |
+
name: MTEB MassiveScenarioClassification (fr)
|
646 |
+
config: fr
|
647 |
+
split: test
|
648 |
+
revision: fad2c6e8459f9e1c45d9315f4953d921437d70f8
|
649 |
+
metrics:
|
650 |
+
- type: accuracy
|
651 |
+
value: 70.68930733019502
|
652 |
+
- type: f1
|
653 |
+
value: 70.26641874846638
|
654 |
+
- type: f1_weighted
|
655 |
+
value: 70.35250466465047
|
656 |
+
- task:
|
657 |
+
type: Retrieval
|
658 |
+
dataset:
|
659 |
+
type: jinaai/mintakaqa
|
660 |
+
name: MTEB MintakaRetrieval (fr)
|
661 |
+
config: fr
|
662 |
+
split: test
|
663 |
+
revision: efa78cc2f74bbcd21eff2261f9e13aebe40b814e
|
664 |
+
metrics:
|
665 |
+
- type: map_at_1
|
666 |
+
value: 19.165
|
667 |
+
- type: map_at_10
|
668 |
+
value: 28.663
|
669 |
+
- type: map_at_100
|
670 |
+
value: 29.737000000000002
|
671 |
+
- type: map_at_1000
|
672 |
+
value: 29.826000000000004
|
673 |
+
- type: map_at_20
|
674 |
+
value: 29.266
|
675 |
+
- type: map_at_3
|
676 |
+
value: 26.024
|
677 |
+
- type: map_at_5
|
678 |
+
value: 27.486
|
679 |
+
- type: mrr_at_1
|
680 |
+
value: 19.164619164619165
|
681 |
+
- type: mrr_at_10
|
682 |
+
value: 28.66298116298116
|
683 |
+
- type: mrr_at_100
|
684 |
+
value: 29.737423308510476
|
685 |
+
- type: mrr_at_1000
|
686 |
+
value: 29.825744096186796
|
687 |
+
- type: mrr_at_20
|
688 |
+
value: 29.26593905045215
|
689 |
+
- type: mrr_at_3
|
690 |
+
value: 26.023751023751025
|
691 |
+
- type: mrr_at_5
|
692 |
+
value: 27.48566748566751
|
693 |
+
- type: nauc_map_at_1000_diff1
|
694 |
+
value: 23.682512151202967
|
695 |
+
- type: nauc_map_at_1000_max
|
696 |
+
value: 25.78708364723919
|
697 |
+
- type: nauc_map_at_100_diff1
|
698 |
+
value: 23.647360144907324
|
699 |
+
- type: nauc_map_at_100_max
|
700 |
+
value: 25.812420160707074
|
701 |
+
- type: nauc_map_at_10_diff1
|
702 |
+
value: 23.658224717435765
|
703 |
+
- type: nauc_map_at_10_max
|
704 |
+
value: 25.845198626323217
|
705 |
+
- type: nauc_map_at_1_diff1
|
706 |
+
value: 30.56830621718086
|
707 |
+
- type: nauc_map_at_1_max
|
708 |
+
value: 19.931526248650147
|
709 |
+
- type: nauc_map_at_20_diff1
|
710 |
+
value: 23.69662048930091
|
711 |
+
- type: nauc_map_at_20_max
|
712 |
+
value: 25.936653022318403
|
713 |
+
- type: nauc_map_at_3_diff1
|
714 |
+
value: 24.663221072349817
|
715 |
+
- type: nauc_map_at_3_max
|
716 |
+
value: 24.634011858800275
|
717 |
+
- type: nauc_map_at_5_diff1
|
718 |
+
value: 24.3650772668551
|
719 |
+
- type: nauc_map_at_5_max
|
720 |
+
value: 25.75222318469224
|
721 |
+
- type: nauc_mrr_at_1000_diff1
|
722 |
+
value: 23.682512151202967
|
723 |
+
- type: nauc_mrr_at_1000_max
|
724 |
+
value: 25.78708364723919
|
725 |
+
- type: nauc_mrr_at_100_diff1
|
726 |
+
value: 23.647360144907324
|
727 |
+
- type: nauc_mrr_at_100_max
|
728 |
+
value: 25.812420160707074
|
729 |
+
- type: nauc_mrr_at_10_diff1
|
730 |
+
value: 23.658224717435765
|
731 |
+
- type: nauc_mrr_at_10_max
|
732 |
+
value: 25.845198626323217
|
733 |
+
- type: nauc_mrr_at_1_diff1
|
734 |
+
value: 30.56830621718086
|
735 |
+
- type: nauc_mrr_at_1_max
|
736 |
+
value: 19.931526248650147
|
737 |
+
- type: nauc_mrr_at_20_diff1
|
738 |
+
value: 23.69662048930091
|
739 |
+
- type: nauc_mrr_at_20_max
|
740 |
+
value: 25.936653022318403
|
741 |
+
- type: nauc_mrr_at_3_diff1
|
742 |
+
value: 24.663221072349817
|
743 |
+
- type: nauc_mrr_at_3_max
|
744 |
+
value: 24.634011858800275
|
745 |
+
- type: nauc_mrr_at_5_diff1
|
746 |
+
value: 24.3650772668551
|
747 |
+
- type: nauc_mrr_at_5_max
|
748 |
+
value: 25.75222318469224
|
749 |
+
- type: nauc_ndcg_at_1000_diff1
|
750 |
+
value: 21.68690756038845
|
751 |
+
- type: nauc_ndcg_at_1000_max
|
752 |
+
value: 27.168575101114893
|
753 |
+
- type: nauc_ndcg_at_100_diff1
|
754 |
+
value: 20.484812648526646
|
755 |
+
- type: nauc_ndcg_at_100_max
|
756 |
+
value: 27.79987215383081
|
757 |
+
- type: nauc_ndcg_at_10_diff1
|
758 |
+
value: 20.791330920997765
|
759 |
+
- type: nauc_ndcg_at_10_max
|
760 |
+
value: 28.272774035036935
|
761 |
+
- type: nauc_ndcg_at_1_diff1
|
762 |
+
value: 30.56830621718086
|
763 |
+
- type: nauc_ndcg_at_1_max
|
764 |
+
value: 19.931526248650147
|
765 |
+
- type: nauc_ndcg_at_20_diff1
|
766 |
+
value: 20.88342749790573
|
767 |
+
- type: nauc_ndcg_at_20_max
|
768 |
+
value: 28.627184419546825
|
769 |
+
- type: nauc_ndcg_at_3_diff1
|
770 |
+
value: 22.987235018840494
|
771 |
+
- type: nauc_ndcg_at_3_max
|
772 |
+
value: 26.054144215976482
|
773 |
+
- type: nauc_ndcg_at_5_diff1
|
774 |
+
value: 22.497863289090464
|
775 |
+
- type: nauc_ndcg_at_5_max
|
776 |
+
value: 27.98879570850259
|
777 |
+
- type: nauc_precision_at_1000_diff1
|
778 |
+
value: -0.6707404502167996
|
779 |
+
- type: nauc_precision_at_1000_max
|
780 |
+
value: 31.987217077673346
|
781 |
+
- type: nauc_precision_at_100_diff1
|
782 |
+
value: 5.079765403021014
|
783 |
+
- type: nauc_precision_at_100_max
|
784 |
+
value: 34.857053312543194
|
785 |
+
- type: nauc_precision_at_10_diff1
|
786 |
+
value: 12.628771618059472
|
787 |
+
- type: nauc_precision_at_10_max
|
788 |
+
value: 35.009564954169896
|
789 |
+
- type: nauc_precision_at_1_diff1
|
790 |
+
value: 30.56830621718086
|
791 |
+
- type: nauc_precision_at_1_max
|
792 |
+
value: 19.931526248650147
|
793 |
+
- type: nauc_precision_at_20_diff1
|
794 |
+
value: 12.28251326261041
|
795 |
+
- type: nauc_precision_at_20_max
|
796 |
+
value: 36.942629359432075
|
797 |
+
- type: nauc_precision_at_3_diff1
|
798 |
+
value: 18.663775283519335
|
799 |
+
- type: nauc_precision_at_3_max
|
800 |
+
value: 29.741315837492472
|
801 |
+
- type: nauc_precision_at_5_diff1
|
802 |
+
value: 17.70442691217025
|
803 |
+
- type: nauc_precision_at_5_max
|
804 |
+
value: 33.93438470540527
|
805 |
+
- type: nauc_recall_at_1000_diff1
|
806 |
+
value: -0.6707404502171719
|
807 |
+
- type: nauc_recall_at_1000_max
|
808 |
+
value: 31.987217077672607
|
809 |
+
- type: nauc_recall_at_100_diff1
|
810 |
+
value: 5.079765403021056
|
811 |
+
- type: nauc_recall_at_100_max
|
812 |
+
value: 34.85705331254323
|
813 |
+
- type: nauc_recall_at_10_diff1
|
814 |
+
value: 12.628771618059483
|
815 |
+
- type: nauc_recall_at_10_max
|
816 |
+
value: 35.00956495416992
|
817 |
+
- type: nauc_recall_at_1_diff1
|
818 |
+
value: 30.56830621718086
|
819 |
+
- type: nauc_recall_at_1_max
|
820 |
+
value: 19.931526248650147
|
821 |
+
- type: nauc_recall_at_20_diff1
|
822 |
+
value: 12.282513262610411
|
823 |
+
- type: nauc_recall_at_20_max
|
824 |
+
value: 36.94262935943207
|
825 |
+
- type: nauc_recall_at_3_diff1
|
826 |
+
value: 18.663775283519346
|
827 |
+
- type: nauc_recall_at_3_max
|
828 |
+
value: 29.741315837492465
|
829 |
+
- type: nauc_recall_at_5_diff1
|
830 |
+
value: 17.704426912170252
|
831 |
+
- type: nauc_recall_at_5_max
|
832 |
+
value: 33.934384705405286
|
833 |
+
- type: ndcg_at_1
|
834 |
+
value: 19.165
|
835 |
+
- type: ndcg_at_10
|
836 |
+
value: 33.674
|
837 |
+
- type: ndcg_at_100
|
838 |
+
value: 39.297
|
839 |
+
- type: ndcg_at_1000
|
840 |
+
value: 41.896
|
841 |
+
- type: ndcg_at_20
|
842 |
+
value: 35.842
|
843 |
+
- type: ndcg_at_3
|
844 |
+
value: 28.238999999999997
|
845 |
+
- type: ndcg_at_5
|
846 |
+
value: 30.863000000000003
|
847 |
+
- type: precision_at_1
|
848 |
+
value: 19.165
|
849 |
+
- type: precision_at_10
|
850 |
+
value: 4.9590000000000005
|
851 |
+
- type: precision_at_100
|
852 |
+
value: 0.768
|
853 |
+
- type: precision_at_1000
|
854 |
+
value: 0.098
|
855 |
+
- type: precision_at_20
|
856 |
+
value: 2.905
|
857 |
+
- type: precision_at_3
|
858 |
+
value: 11.548
|
859 |
+
- type: precision_at_5
|
860 |
+
value: 8.198
|
861 |
+
- type: recall_at_1
|
862 |
+
value: 19.165
|
863 |
+
- type: recall_at_10
|
864 |
+
value: 49.59
|
865 |
+
- type: recall_at_100
|
866 |
+
value: 76.822
|
867 |
+
- type: recall_at_1000
|
868 |
+
value: 97.83
|
869 |
+
- type: recall_at_20
|
870 |
+
value: 58.108000000000004
|
871 |
+
- type: recall_at_3
|
872 |
+
value: 34.644000000000005
|
873 |
+
- type: recall_at_5
|
874 |
+
value: 40.991
|
875 |
+
- task:
|
876 |
+
type: PairClassification
|
877 |
+
dataset:
|
878 |
+
type: GEM/opusparcus
|
879 |
+
name: MTEB OpusparcusPC (fr)
|
880 |
+
config: fr
|
881 |
+
split: test
|
882 |
+
revision: 9e9b1f8ef51616073f47f306f7f47dd91663f86a
|
883 |
+
metrics:
|
884 |
+
- type: cos_sim_accuracy
|
885 |
+
value: 83.51498637602179
|
886 |
+
- type: cos_sim_ap
|
887 |
+
value: 94.18614574224773
|
888 |
+
- type: cos_sim_f1
|
889 |
+
value: 88.3564925730714
|
890 |
+
- type: cos_sim_precision
|
891 |
+
value: 85.37037037037037
|
892 |
+
- type: cos_sim_recall
|
893 |
+
value: 91.55908639523337
|
894 |
+
- type: dot_accuracy
|
895 |
+
value: 83.51498637602179
|
896 |
+
- type: dot_ap
|
897 |
+
value: 94.18614574224773
|
898 |
+
- type: dot_f1
|
899 |
+
value: 88.3564925730714
|
900 |
+
- type: dot_precision
|
901 |
+
value: 85.37037037037037
|
902 |
+
- type: dot_recall
|
903 |
+
value: 91.55908639523337
|
904 |
+
- type: euclidean_accuracy
|
905 |
+
value: 83.51498637602179
|
906 |
+
- type: euclidean_ap
|
907 |
+
value: 94.18614574224773
|
908 |
+
- type: euclidean_f1
|
909 |
+
value: 88.3564925730714
|
910 |
+
- type: euclidean_precision
|
911 |
+
value: 85.37037037037037
|
912 |
+
- type: euclidean_recall
|
913 |
+
value: 91.55908639523337
|
914 |
+
- type: manhattan_accuracy
|
915 |
+
value: 83.51498637602179
|
916 |
+
- type: manhattan_ap
|
917 |
+
value: 94.16717671332795
|
918 |
+
- type: manhattan_f1
|
919 |
+
value: 88.35418671799807
|
920 |
+
- type: manhattan_precision
|
921 |
+
value: 85.71428571428571
|
922 |
+
- type: manhattan_recall
|
923 |
+
value: 91.16186693147964
|
924 |
+
- type: max_accuracy
|
925 |
+
value: 83.51498637602179
|
926 |
+
- type: max_ap
|
927 |
+
value: 94.18614574224773
|
928 |
+
- type: max_f1
|
929 |
+
value: 88.3564925730714
|
930 |
+
- task:
|
931 |
+
type: PairClassification
|
932 |
+
dataset:
|
933 |
+
type: google-research-datasets/paws-x
|
934 |
+
name: MTEB PawsX (fr)
|
935 |
+
config: fr
|
936 |
+
split: test
|
937 |
+
revision: 8a04d940a42cd40658986fdd8e3da561533a3646
|
938 |
+
metrics:
|
939 |
+
- type: cos_sim_accuracy
|
940 |
+
value: 60.699999999999996
|
941 |
+
- type: cos_sim_ap
|
942 |
+
value: 60.20276173325004
|
943 |
+
- type: cos_sim_f1
|
944 |
+
value: 62.716429395921516
|
945 |
+
- type: cos_sim_precision
|
946 |
+
value: 48.05424528301887
|
947 |
+
- type: cos_sim_recall
|
948 |
+
value: 90.2547065337763
|
949 |
+
- type: dot_accuracy
|
950 |
+
value: 60.699999999999996
|
951 |
+
- type: dot_ap
|
952 |
+
value: 60.27996470746299
|
953 |
+
- type: dot_f1
|
954 |
+
value: 62.716429395921516
|
955 |
+
- type: dot_precision
|
956 |
+
value: 48.05424528301887
|
957 |
+
- type: dot_recall
|
958 |
+
value: 90.2547065337763
|
959 |
+
- type: euclidean_accuracy
|
960 |
+
value: 60.699999999999996
|
961 |
+
- type: euclidean_ap
|
962 |
+
value: 60.20276173325004
|
963 |
+
- type: euclidean_f1
|
964 |
+
value: 62.716429395921516
|
965 |
+
- type: euclidean_precision
|
966 |
+
value: 48.05424528301887
|
967 |
+
- type: euclidean_recall
|
968 |
+
value: 90.2547065337763
|
969 |
+
- type: manhattan_accuracy
|
970 |
+
value: 60.699999999999996
|
971 |
+
- type: manhattan_ap
|
972 |
+
value: 60.18010040913353
|
973 |
+
- type: manhattan_f1
|
974 |
+
value: 62.71056661562021
|
975 |
+
- type: manhattan_precision
|
976 |
+
value: 47.92276184903452
|
977 |
+
- type: manhattan_recall
|
978 |
+
value: 90.69767441860465
|
979 |
+
- type: max_accuracy
|
980 |
+
value: 60.699999999999996
|
981 |
+
- type: max_ap
|
982 |
+
value: 60.27996470746299
|
983 |
+
- type: max_f1
|
984 |
+
value: 62.716429395921516
|
985 |
+
- task:
|
986 |
+
type: STS
|
987 |
+
dataset:
|
988 |
+
type: Lajavaness/SICK-fr
|
989 |
+
name: MTEB SICKFr
|
990 |
+
config: default
|
991 |
+
split: test
|
992 |
+
revision: e077ab4cf4774a1e36d86d593b150422fafd8e8a
|
993 |
+
metrics:
|
994 |
+
- type: cos_sim_pearson
|
995 |
+
value: 84.24496945719946
|
996 |
+
- type: cos_sim_spearman
|
997 |
+
value: 78.10001513346513
|
998 |
+
- type: euclidean_pearson
|
999 |
+
value: 81.43570951228163
|
1000 |
+
- type: euclidean_spearman
|
1001 |
+
value: 78.0987784421045
|
1002 |
+
- type: manhattan_pearson
|
1003 |
+
value: 81.31986646517238
|
1004 |
+
- type: manhattan_spearman
|
1005 |
+
value: 78.09610194828534
|
1006 |
+
- task:
|
1007 |
+
type: STS
|
1008 |
+
dataset:
|
1009 |
+
type: mteb/sts22-crosslingual-sts
|
1010 |
+
name: MTEB STS22 (fr)
|
1011 |
+
config: fr
|
1012 |
+
split: test
|
1013 |
+
revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3
|
1014 |
+
metrics:
|
1015 |
+
- type: cos_sim_pearson
|
1016 |
+
value: 83.07721141521425
|
1017 |
+
- type: cos_sim_spearman
|
1018 |
+
value: 83.19199466052186
|
1019 |
+
- type: euclidean_pearson
|
1020 |
+
value: 82.10672022294766
|
1021 |
+
- type: euclidean_spearman
|
1022 |
+
value: 83.19199466052186
|
1023 |
+
- type: manhattan_pearson
|
1024 |
+
value: 81.92531847793633
|
1025 |
+
- type: manhattan_spearman
|
1026 |
+
value: 83.20694689089673
|
1027 |
+
- task:
|
1028 |
+
type: STS
|
1029 |
+
dataset:
|
1030 |
+
type: mteb/stsb_multi_mt
|
1031 |
+
name: MTEB STSBenchmarkMultilingualSTS (fr)
|
1032 |
+
config: fr
|
1033 |
+
split: test
|
1034 |
+
revision: 29afa2569dcedaaa2fe6a3dcfebab33d28b82e8c
|
1035 |
+
metrics:
|
1036 |
+
- type: cos_sim_pearson
|
1037 |
+
value: 83.957481748094
|
1038 |
+
- type: cos_sim_spearman
|
1039 |
+
value: 84.40492503459248
|
1040 |
+
- type: euclidean_pearson
|
1041 |
+
value: 83.8150014101056
|
1042 |
+
- type: euclidean_spearman
|
1043 |
+
value: 84.40686653864509
|
1044 |
+
- type: manhattan_pearson
|
1045 |
+
value: 83.6816837321264
|
1046 |
+
- type: manhattan_spearman
|
1047 |
+
value: 84.2678486368702
|
1048 |
+
- task:
|
1049 |
+
type: Summarization
|
1050 |
+
dataset:
|
1051 |
+
type: lyon-nlp/summarization-summeval-fr-p2p
|
1052 |
+
name: MTEB SummEvalFr
|
1053 |
+
config: default
|
1054 |
+
split: test
|
1055 |
+
revision: b385812de6a9577b6f4d0f88c6a6e35395a94054
|
1056 |
+
metrics:
|
1057 |
+
- type: cos_sim_pearson
|
1058 |
+
value: 32.06592630917136
|
1059 |
+
- type: cos_sim_spearman
|
1060 |
+
value: 30.94878864229808
|
1061 |
+
- type: dot_pearson
|
1062 |
+
value: 32.06591974515864
|
1063 |
+
- type: dot_spearman
|
1064 |
+
value: 30.925383080565222
|
1065 |
+
- task:
|
1066 |
+
type: Reranking
|
1067 |
+
dataset:
|
1068 |
+
type: lyon-nlp/mteb-fr-reranking-syntec-s2p
|
1069 |
+
name: MTEB SyntecReranking
|
1070 |
+
config: default
|
1071 |
+
split: test
|
1072 |
+
revision: daf0863838cd9e3ba50544cdce3ac2b338a1b0ad
|
1073 |
+
metrics:
|
1074 |
+
- type: map
|
1075 |
+
value: 88.11666666666667
|
1076 |
+
- type: mrr
|
1077 |
+
value: 88.11666666666667
|
1078 |
+
- type: nAUC_map_diff1
|
1079 |
+
value: 66.27779227667267
|
1080 |
+
- type: nAUC_map_max
|
1081 |
+
value: 6.651414764738896
|
1082 |
+
- type: nAUC_mrr_diff1
|
1083 |
+
value: 66.27779227667267
|
1084 |
+
- type: nAUC_mrr_max
|
1085 |
+
value: 6.651414764738896
|
1086 |
+
- task:
|
1087 |
+
type: Retrieval
|
1088 |
+
dataset:
|
1089 |
+
type: lyon-nlp/mteb-fr-retrieval-syntec-s2p
|
1090 |
+
name: MTEB SyntecRetrieval
|
1091 |
+
config: default
|
1092 |
+
split: test
|
1093 |
+
revision: 19661ccdca4dfc2d15122d776b61685f48c68ca9
|
1094 |
+
metrics:
|
1095 |
+
- type: map_at_1
|
1096 |
+
value: 69.0
|
1097 |
+
- type: map_at_10
|
1098 |
+
value: 80.65
|
1099 |
+
- type: map_at_100
|
1100 |
+
value: 80.838
|
1101 |
+
- type: map_at_1000
|
1102 |
+
value: 80.838
|
1103 |
+
- type: map_at_20
|
1104 |
+
value: 80.838
|
1105 |
+
- type: map_at_3
|
1106 |
+
value: 79.833
|
1107 |
+
- type: map_at_5
|
1108 |
+
value: 80.483
|
1109 |
+
- type: mrr_at_1
|
1110 |
+
value: 69.0
|
1111 |
+
- type: mrr_at_10
|
1112 |
+
value: 80.64999999999999
|
1113 |
+
- type: mrr_at_100
|
1114 |
+
value: 80.83799019607844
|
1115 |
+
- type: mrr_at_1000
|
1116 |
+
value: 80.83799019607844
|
1117 |
+
- type: mrr_at_20
|
1118 |
+
value: 80.83799019607844
|
1119 |
+
- type: mrr_at_3
|
1120 |
+
value: 79.83333333333334
|
1121 |
+
- type: mrr_at_5
|
1122 |
+
value: 80.48333333333333
|
1123 |
+
- type: nauc_map_at_1000_diff1
|
1124 |
+
value: 61.46904865740055
|
1125 |
+
- type: nauc_map_at_1000_max
|
1126 |
+
value: 24.307826758747282
|
1127 |
+
- type: nauc_map_at_100_diff1
|
1128 |
+
value: 61.46904865740055
|
1129 |
+
- type: nauc_map_at_100_max
|
1130 |
+
value: 24.307826758747282
|
1131 |
+
- type: nauc_map_at_10_diff1
|
1132 |
+
value: 61.094194035098035
|
1133 |
+
- type: nauc_map_at_10_max
|
1134 |
+
value: 24.44687875369869
|
1135 |
+
- type: nauc_map_at_1_diff1
|
1136 |
+
value: 65.17628798701865
|
1137 |
+
- type: nauc_map_at_1_max
|
1138 |
+
value: 25.79501560929155
|
1139 |
+
- type: nauc_map_at_20_diff1
|
1140 |
+
value: 61.46904865740055
|
1141 |
+
- type: nauc_map_at_20_max
|
1142 |
+
value: 24.307826758747282
|
1143 |
+
- type: nauc_map_at_3_diff1
|
1144 |
+
value: 61.562719756100805
|
1145 |
+
- type: nauc_map_at_3_max
|
1146 |
+
value: 25.87804164282553
|
1147 |
+
- type: nauc_map_at_5_diff1
|
1148 |
+
value: 61.471976470716264
|
1149 |
+
- type: nauc_map_at_5_max
|
1150 |
+
value: 25.180513270581322
|
1151 |
+
- type: nauc_mrr_at_1000_diff1
|
1152 |
+
value: 61.46904865740055
|
1153 |
+
- type: nauc_mrr_at_1000_max
|
1154 |
+
value: 24.307826758747282
|
1155 |
+
- type: nauc_mrr_at_100_diff1
|
1156 |
+
value: 61.46904865740055
|
1157 |
+
- type: nauc_mrr_at_100_max
|
1158 |
+
value: 24.307826758747282
|
1159 |
+
- type: nauc_mrr_at_10_diff1
|
1160 |
+
value: 61.094194035098035
|
1161 |
+
- type: nauc_mrr_at_10_max
|
1162 |
+
value: 24.44687875369869
|
1163 |
+
- type: nauc_mrr_at_1_diff1
|
1164 |
+
value: 65.17628798701865
|
1165 |
+
- type: nauc_mrr_at_1_max
|
1166 |
+
value: 25.79501560929155
|
1167 |
+
- type: nauc_mrr_at_20_diff1
|
1168 |
+
value: 61.46904865740055
|
1169 |
+
- type: nauc_mrr_at_20_max
|
1170 |
+
value: 24.307826758747282
|
1171 |
+
- type: nauc_mrr_at_3_diff1
|
1172 |
+
value: 61.562719756100805
|
1173 |
+
- type: nauc_mrr_at_3_max
|
1174 |
+
value: 25.87804164282553
|
1175 |
+
- type: nauc_mrr_at_5_diff1
|
1176 |
+
value: 61.471976470716264
|
1177 |
+
- type: nauc_mrr_at_5_max
|
1178 |
+
value: 25.180513270581322
|
1179 |
+
- type: nauc_ndcg_at_1000_diff1
|
1180 |
+
value: 60.95477865546023
|
1181 |
+
- type: nauc_ndcg_at_1000_max
|
1182 |
+
value: 24.427553593893535
|
1183 |
+
- type: nauc_ndcg_at_100_diff1
|
1184 |
+
value: 60.95477865546023
|
1185 |
+
- type: nauc_ndcg_at_100_max
|
1186 |
+
value: 24.427553593893535
|
1187 |
+
- type: nauc_ndcg_at_10_diff1
|
1188 |
+
value: 59.101673931307396
|
1189 |
+
- type: nauc_ndcg_at_10_max
|
1190 |
+
value: 25.01155211084955
|
1191 |
+
- type: nauc_ndcg_at_1_diff1
|
1192 |
+
value: 65.17628798701865
|
1193 |
+
- type: nauc_ndcg_at_1_max
|
1194 |
+
value: 25.79501560929155
|
1195 |
+
- type: nauc_ndcg_at_20_diff1
|
1196 |
+
value: 60.95477865546023
|
1197 |
+
- type: nauc_ndcg_at_20_max
|
1198 |
+
value: 24.427553593893535
|
1199 |
+
- type: nauc_ndcg_at_3_diff1
|
1200 |
+
value: 60.333057480044616
|
1201 |
+
- type: nauc_ndcg_at_3_max
|
1202 |
+
value: 28.363238330232637
|
1203 |
+
- type: nauc_ndcg_at_5_diff1
|
1204 |
+
value: 60.15511994533307
|
1205 |
+
- type: nauc_ndcg_at_5_max
|
1206 |
+
value: 26.94308058940176
|
1207 |
+
- type: nauc_precision_at_1000_diff1
|
1208 |
+
value: nan
|
1209 |
+
- type: nauc_precision_at_1000_max
|
1210 |
+
value: nan
|
1211 |
+
- type: nauc_precision_at_100_diff1
|
1212 |
+
value: nan
|
1213 |
+
- type: nauc_precision_at_100_max
|
1214 |
+
value: nan
|
1215 |
+
- type: nauc_precision_at_10_diff1
|
1216 |
+
value: 26.657329598506518
|
1217 |
+
- type: nauc_precision_at_10_max
|
1218 |
+
value: 34.26704014939361
|
1219 |
+
- type: nauc_precision_at_1_diff1
|
1220 |
+
value: 65.17628798701865
|
1221 |
+
- type: nauc_precision_at_1_max
|
1222 |
+
value: 25.79501560929155
|
1223 |
+
- type: nauc_precision_at_20_diff1
|
1224 |
+
value: 100.0
|
1225 |
+
- type: nauc_precision_at_20_max
|
1226 |
+
value: 100.0
|
1227 |
+
- type: nauc_precision_at_3_diff1
|
1228 |
+
value: 51.834066960117276
|
1229 |
+
- type: nauc_precision_at_3_max
|
1230 |
+
value: 48.25930372148875
|
1231 |
+
- type: nauc_precision_at_5_diff1
|
1232 |
+
value: 44.992997198879706
|
1233 |
+
- type: nauc_precision_at_5_max
|
1234 |
+
value: 50.70028011204499
|
1235 |
+
- type: nauc_recall_at_1000_diff1
|
1236 |
+
value: nan
|
1237 |
+
- type: nauc_recall_at_1000_max
|
1238 |
+
value: nan
|
1239 |
+
- type: nauc_recall_at_100_diff1
|
1240 |
+
value: nan
|
1241 |
+
- type: nauc_recall_at_100_max
|
1242 |
+
value: nan
|
1243 |
+
- type: nauc_recall_at_10_diff1
|
1244 |
+
value: 26.657329598505903
|
1245 |
+
- type: nauc_recall_at_10_max
|
1246 |
+
value: 34.26704014939303
|
1247 |
+
- type: nauc_recall_at_1_diff1
|
1248 |
+
value: 65.17628798701865
|
1249 |
+
- type: nauc_recall_at_1_max
|
1250 |
+
value: 25.79501560929155
|
1251 |
+
- type: nauc_recall_at_20_diff1
|
1252 |
+
value: nan
|
1253 |
+
- type: nauc_recall_at_20_max
|
1254 |
+
value: nan
|
1255 |
+
- type: nauc_recall_at_3_diff1
|
1256 |
+
value: 51.834066960117376
|
1257 |
+
- type: nauc_recall_at_3_max
|
1258 |
+
value: 48.25930372148865
|
1259 |
+
- type: nauc_recall_at_5_diff1
|
1260 |
+
value: 44.99299719887955
|
1261 |
+
- type: nauc_recall_at_5_max
|
1262 |
+
value: 50.70028011204488
|
1263 |
+
- type: ndcg_at_1
|
1264 |
+
value: 69.0
|
1265 |
+
- type: ndcg_at_10
|
1266 |
+
value: 84.786
|
1267 |
+
- type: ndcg_at_100
|
1268 |
+
value: 85.521
|
1269 |
+
- type: ndcg_at_1000
|
1270 |
+
value: 85.521
|
1271 |
+
- type: ndcg_at_20
|
1272 |
+
value: 85.521
|
1273 |
+
- type: ndcg_at_3
|
1274 |
+
value: 83.226
|
1275 |
+
- type: ndcg_at_5
|
1276 |
+
value: 84.43
|
1277 |
+
- type: precision_at_1
|
1278 |
+
value: 69.0
|
1279 |
+
- type: precision_at_10
|
1280 |
+
value: 9.700000000000001
|
1281 |
+
- type: precision_at_100
|
1282 |
+
value: 1.0
|
1283 |
+
- type: precision_at_1000
|
1284 |
+
value: 0.1
|
1285 |
+
- type: precision_at_20
|
1286 |
+
value: 5.0
|
1287 |
+
- type: precision_at_3
|
1288 |
+
value: 31.0
|
1289 |
+
- type: precision_at_5
|
1290 |
+
value: 19.2
|
1291 |
+
- type: recall_at_1
|
1292 |
+
value: 69.0
|
1293 |
+
- type: recall_at_10
|
1294 |
+
value: 97.0
|
1295 |
+
- type: recall_at_100
|
1296 |
+
value: 100.0
|
1297 |
+
- type: recall_at_1000
|
1298 |
+
value: 100.0
|
1299 |
+
- type: recall_at_20
|
1300 |
+
value: 100.0
|
1301 |
+
- type: recall_at_3
|
1302 |
+
value: 93.0
|
1303 |
+
- type: recall_at_5
|
1304 |
+
value: 96.0
|
1305 |
+
- task:
|
1306 |
+
type: Retrieval
|
1307 |
+
dataset:
|
1308 |
+
type: jinaai/xpqa
|
1309 |
+
name: MTEB XPQARetrieval (fr)
|
1310 |
+
config: fr
|
1311 |
+
split: test
|
1312 |
+
revision: c99d599f0a6ab9b85b065da6f9d94f9cf731679f
|
1313 |
+
metrics:
|
1314 |
+
- type: map_at_1
|
1315 |
+
value: 40.797
|
1316 |
+
- type: map_at_10
|
1317 |
+
value: 62.71099999999999
|
1318 |
+
- type: map_at_100
|
1319 |
+
value: 64.261
|
1320 |
+
- type: map_at_1000
|
1321 |
+
value: 64.306
|
1322 |
+
- type: map_at_20
|
1323 |
+
value: 63.693
|
1324 |
+
- type: map_at_3
|
1325 |
+
value: 56.686
|
1326 |
+
- type: map_at_5
|
1327 |
+
value: 60.653999999999996
|
1328 |
+
- type: mrr_at_1
|
1329 |
+
value: 64.08544726301736
|
1330 |
+
- type: mrr_at_10
|
1331 |
+
value: 71.24790726259349
|
1332 |
+
- type: mrr_at_100
|
1333 |
+
value: 71.7835679704396
|
1334 |
+
- type: mrr_at_1000
|
1335 |
+
value: 71.79095567140973
|
1336 |
+
- type: mrr_at_20
|
1337 |
+
value: 71.5854708410262
|
1338 |
+
- type: mrr_at_3
|
1339 |
+
value: 69.55941255006672
|
1340 |
+
- type: mrr_at_5
|
1341 |
+
value: 70.60747663551396
|
1342 |
+
- type: nauc_map_at_1000_diff1
|
1343 |
+
value: 47.803181417639365
|
1344 |
+
- type: nauc_map_at_1000_max
|
1345 |
+
value: 51.22073368230412
|
1346 |
+
- type: nauc_map_at_100_diff1
|
1347 |
+
value: 47.771573391555755
|
1348 |
+
- type: nauc_map_at_100_max
|
1349 |
+
value: 51.20370234778812
|
1350 |
+
- type: nauc_map_at_10_diff1
|
1351 |
+
value: 47.340833389771625
|
1352 |
+
- type: nauc_map_at_10_max
|
1353 |
+
value: 50.41256517180715
|
1354 |
+
- type: nauc_map_at_1_diff1
|
1355 |
+
value: 55.14983744702445
|
1356 |
+
- type: nauc_map_at_1_max
|
1357 |
+
value: 31.104750896985728
|
1358 |
+
- type: nauc_map_at_20_diff1
|
1359 |
+
value: 47.64026863999484
|
1360 |
+
- type: nauc_map_at_20_max
|
1361 |
+
value: 50.87670909266768
|
1362 |
+
- type: nauc_map_at_3_diff1
|
1363 |
+
value: 47.681906747352635
|
1364 |
+
- type: nauc_map_at_3_max
|
1365 |
+
value: 43.47246277661219
|
1366 |
+
- type: nauc_map_at_5_diff1
|
1367 |
+
value: 46.874943002794815
|
1368 |
+
- type: nauc_map_at_5_max
|
1369 |
+
value: 48.469495140739724
|
1370 |
+
- type: nauc_mrr_at_1000_diff1
|
1371 |
+
value: 57.34098736669957
|
1372 |
+
- type: nauc_mrr_at_1000_max
|
1373 |
+
value: 60.179095583193444
|
1374 |
+
- type: nauc_mrr_at_100_diff1
|
1375 |
+
value: 57.339862158018796
|
1376 |
+
- type: nauc_mrr_at_100_max
|
1377 |
+
value: 60.18082273539442
|
1378 |
+
- type: nauc_mrr_at_10_diff1
|
1379 |
+
value: 57.210874058908814
|
1380 |
+
- type: nauc_mrr_at_10_max
|
1381 |
+
value: 60.043680803697086
|
1382 |
+
- type: nauc_mrr_at_1_diff1
|
1383 |
+
value: 59.69074056197331
|
1384 |
+
- type: nauc_mrr_at_1_max
|
1385 |
+
value: 60.90082316300324
|
1386 |
+
- type: nauc_mrr_at_20_diff1
|
1387 |
+
value: 57.35434243512763
|
1388 |
+
- type: nauc_mrr_at_20_max
|
1389 |
+
value: 60.18873377253912
|
1390 |
+
- type: nauc_mrr_at_3_diff1
|
1391 |
+
value: 57.26933631425754
|
1392 |
+
- type: nauc_mrr_at_3_max
|
1393 |
+
value: 60.05458089795687
|
1394 |
+
- type: nauc_mrr_at_5_diff1
|
1395 |
+
value: 57.045411517214276
|
1396 |
+
- type: nauc_mrr_at_5_max
|
1397 |
+
value: 59.981421712413685
|
1398 |
+
- type: nauc_ndcg_at_1000_diff1
|
1399 |
+
value: 50.232929738614814
|
1400 |
+
- type: nauc_ndcg_at_1000_max
|
1401 |
+
value: 55.01594185277396
|
1402 |
+
- type: nauc_ndcg_at_100_diff1
|
1403 |
+
value: 49.876825728406786
|
1404 |
+
- type: nauc_ndcg_at_100_max
|
1405 |
+
value: 54.87898182661215
|
1406 |
+
- type: nauc_ndcg_at_10_diff1
|
1407 |
+
value: 48.40787615482867
|
1408 |
+
- type: nauc_ndcg_at_10_max
|
1409 |
+
value: 52.84877289626636
|
1410 |
+
- type: nauc_ndcg_at_1_diff1
|
1411 |
+
value: 59.69074056197331
|
1412 |
+
- type: nauc_ndcg_at_1_max
|
1413 |
+
value: 60.90082316300324
|
1414 |
+
- type: nauc_ndcg_at_20_diff1
|
1415 |
+
value: 49.08453974591539
|
1416 |
+
- type: nauc_ndcg_at_20_max
|
1417 |
+
value: 53.80319392912378
|
1418 |
+
- type: nauc_ndcg_at_3_diff1
|
1419 |
+
value: 48.21830414023458
|
1420 |
+
- type: nauc_ndcg_at_3_max
|
1421 |
+
value: 51.321799626032714
|
1422 |
+
- type: nauc_ndcg_at_5_diff1
|
1423 |
+
value: 47.614495954542605
|
1424 |
+
- type: nauc_ndcg_at_5_max
|
1425 |
+
value: 50.803800463597405
|
1426 |
+
- type: nauc_precision_at_1000_diff1
|
1427 |
+
value: -15.87250509394414
|
1428 |
+
- type: nauc_precision_at_1000_max
|
1429 |
+
value: 16.09830137145176
|
1430 |
+
- type: nauc_precision_at_100_diff1
|
1431 |
+
value: -13.720930651556534
|
1432 |
+
- type: nauc_precision_at_100_max
|
1433 |
+
value: 19.94363871765946
|
1434 |
+
- type: nauc_precision_at_10_diff1
|
1435 |
+
value: -3.9626074014054136
|
1436 |
+
- type: nauc_precision_at_10_max
|
1437 |
+
value: 30.48732389685921
|
1438 |
+
- type: nauc_precision_at_1_diff1
|
1439 |
+
value: 59.69074056197331
|
1440 |
+
- type: nauc_precision_at_1_max
|
1441 |
+
value: 60.90082316300324
|
1442 |
+
- type: nauc_precision_at_20_diff1
|
1443 |
+
value: -8.144148640034853
|
1444 |
+
- type: nauc_precision_at_20_max
|
1445 |
+
value: 26.183545158653338
|
1446 |
+
- type: nauc_precision_at_3_diff1
|
1447 |
+
value: 7.1166818076254605
|
1448 |
+
- type: nauc_precision_at_3_max
|
1449 |
+
value: 37.64665636029093
|
1450 |
+
- type: nauc_precision_at_5_diff1
|
1451 |
+
value: 0.3455996928663316
|
1452 |
+
- type: nauc_precision_at_5_max
|
1453 |
+
value: 34.95245204298077
|
1454 |
+
- type: nauc_recall_at_1000_diff1
|
1455 |
+
value: 47.93171740380228
|
1456 |
+
- type: nauc_recall_at_1000_max
|
1457 |
+
value: 89.21354057542635
|
1458 |
+
- type: nauc_recall_at_100_diff1
|
1459 |
+
value: 34.93973412699365
|
1460 |
+
- type: nauc_recall_at_100_max
|
1461 |
+
value: 47.89216950421148
|
1462 |
+
- type: nauc_recall_at_10_diff1
|
1463 |
+
value: 38.58556368247737
|
1464 |
+
- type: nauc_recall_at_10_max
|
1465 |
+
value: 45.13227163006313
|
1466 |
+
- type: nauc_recall_at_1_diff1
|
1467 |
+
value: 55.14983744702445
|
1468 |
+
- type: nauc_recall_at_1_max
|
1469 |
+
value: 31.104750896985728
|
1470 |
+
- type: nauc_recall_at_20_diff1
|
1471 |
+
value: 38.53568097509877
|
1472 |
+
- type: nauc_recall_at_20_max
|
1473 |
+
value: 46.37328875121808
|
1474 |
+
- type: nauc_recall_at_3_diff1
|
1475 |
+
value: 41.49659886305561
|
1476 |
+
- type: nauc_recall_at_3_max
|
1477 |
+
value: 38.59476562231703
|
1478 |
+
- type: nauc_recall_at_5_diff1
|
1479 |
+
value: 38.489499442628016
|
1480 |
+
- type: nauc_recall_at_5_max
|
1481 |
+
value: 43.06848825600403
|
1482 |
+
- type: ndcg_at_1
|
1483 |
+
value: 64.08500000000001
|
1484 |
+
- type: ndcg_at_10
|
1485 |
+
value: 68.818
|
1486 |
+
- type: ndcg_at_100
|
1487 |
+
value: 73.66
|
1488 |
+
- type: ndcg_at_1000
|
1489 |
+
value: 74.309
|
1490 |
+
- type: ndcg_at_20
|
1491 |
+
value: 71.147
|
1492 |
+
- type: ndcg_at_3
|
1493 |
+
value: 64.183
|
1494 |
+
- type: ndcg_at_5
|
1495 |
+
value: 65.668
|
1496 |
+
- type: precision_at_1
|
1497 |
+
value: 64.08500000000001
|
1498 |
+
- type: precision_at_10
|
1499 |
+
value: 15.728
|
1500 |
+
- type: precision_at_100
|
1501 |
+
value: 1.9720000000000002
|
1502 |
+
- type: precision_at_1000
|
1503 |
+
value: 0.207
|
1504 |
+
- type: precision_at_20
|
1505 |
+
value: 8.705
|
1506 |
+
- type: precision_at_3
|
1507 |
+
value: 39.03
|
1508 |
+
- type: precision_at_5
|
1509 |
+
value: 27.717000000000002
|
1510 |
+
- type: recall_at_1
|
1511 |
+
value: 40.797
|
1512 |
+
- type: recall_at_10
|
1513 |
+
value: 77.432
|
1514 |
+
- type: recall_at_100
|
1515 |
+
value: 95.68100000000001
|
1516 |
+
- type: recall_at_1000
|
1517 |
+
value: 99.666
|
1518 |
+
- type: recall_at_20
|
1519 |
+
value: 84.773
|
1520 |
+
- type: recall_at_3
|
1521 |
+
value: 62.083
|
1522 |
+
- type: recall_at_5
|
1523 |
+
value: 69.786
|
1524 |
license: apache-2.0
|
1525 |
language:
|
1526 |
- fr
|
1527 |
- en
|
|
|
|
|
|
|
1528 |
---
|
1529 |
## Model Description:
|
1530 |
+
[**french-document-embedding**](https://huggingface.co/dangvantuan/french-document-embedding) is an embedding model for documents in the French-English language, with a context length of up to 8096 tokens. This model is a specialized text-embedding model trained specifically for the French-English language. It is built upon [gte-multilingual](Alibaba-NLP/gte-multilingual-base) and trained using the [SimilarityLoss], [Multi-Negative Ranking Loss](https://arxiv.org/abs/1705.00652), [Matryoshka2dLoss](https://arxiv.org/html/2402.14776v1) and [GISTEmbedLoss](https://arxiv.org/abs/2402.16829) using [guide model](https://huggingface.co/Lajavaness/bilingual-embedding-large). This model embeds and converts long texts or documents into vectors with 786 dimensions, making it useful for vector databases serving semantic search or RAG (Retrieval-Augmented Generation).
|
1531 |
|
1532 |
## Full Model Architecture
|
1533 |
```
|
|
|
1537 |
(2): Normalize()
|
1538 |
)
|
1539 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1540 |
|
1541 |
|
1542 |
## Usage:
|
|
|
1555 |
|
1556 |
|
1557 |
|
1558 |
+
model = SentenceTransformer('dangvantuan/french-document-embedding', trust_remote_code=True)
|
1559 |
embeddings = model.encode(sentences)
|
1560 |
print(embeddings)
|
1561 |
|
|
|
1579 |
year={2019}
|
1580 |
}
|
1581 |
|
|
|
1582 |
@article{zhang2024mgte,
|
1583 |
title={mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval},
|
1584 |
author={Zhang, Xin and Zhang, Yanzhao and Long, Dingkun and Xie, Wen and Dai, Ziqi and Tang, Jialong and Lin, Huan and Yang, Baosong and Xie, Pengjun and Huang, Fei and others},
|
|
|
1598 |
author={Li, Xianming and Li, Zongxi and Li, Jing and Xie, Haoran and Li, Qing},
|
1599 |
journal={arXiv preprint arXiv:2402.14776},
|
1600 |
year={2024}
|
1601 |
+
}
|
1602 |
+
|
1603 |
+
@misc{henderson2017efficient,
|
1604 |
+
title={Efficient Natural Language Response Suggestion for Smart Reply},
|
1605 |
+
author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
|
1606 |
+
year={2017},
|
1607 |
+
eprint={1705.00652},
|
1608 |
+
archivePrefix={arXiv},
|
1609 |
+
primaryClass={cs.CL}
|
1610 |
+
}
|
1611 |
+
|
1612 |
+
@misc{solatorio2024gistembed,
|
1613 |
+
title={GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning},
|
1614 |
+
author={Aivin V. Solatorio},
|
1615 |
+
year={2024},
|
1616 |
+
eprint={2402.16829},
|
1617 |
+
archivePrefix={arXiv},
|
1618 |
+
primaryClass={cs.LG}
|
1619 |
}
|