dangvantuan
commited on
Commit
•
246cb1d
1
Parent(s):
3c04b3d
Update README.md
Browse files
README.md
CHANGED
@@ -24,9 +24,11 @@ model-index:
|
|
24 |
type: Pearson_correlation_coefficient
|
25 |
value: xx.xx
|
26 |
---
|
|
|
|
|
27 |
|
28 |
-
## Pre-trained sentence embedding models are
|
29 |
-
|
30 |
[Siamese BERT-Networks with 'sentences-transformers'](https://www.sbert.net/) on dataset [stsb](https://huggingface.co/datasets/stsb_multi_mt/viewer/fr/train)
|
31 |
|
32 |
|
@@ -90,6 +92,7 @@ The performance is measured using Pearson and Spearman correlation:
|
|
90 |
| [dangvantuan/sentence-camembert-large](https://huggingface.co/dangvantuan/sentence-camembert-large)| 88.2 |88.02 | 336M|
|
91 |
| [dangvantuan/sentence-camembert-base](https://huggingface.co/dangvantuan/sentence-camembert-base) | 86.73|86.54 | 110M |
|
92 |
| [distiluse-base-multilingual-cased](https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased) | 79.22 | 79.16|135M |
|
|
|
93 |
- On test
|
94 |
|
95 |
|
@@ -98,6 +101,7 @@ The performance is measured using Pearson and Spearman correlation:
|
|
98 |
| [dangvantuan/sentence-camembert-large](https://huggingface.co/dangvantuan/sentence-camembert-large)| 85.9 | 85.8|
|
99 |
| [dangvantuan/sentence-camembert-base](https://huggingface.co/dangvantuan/sentence-camembert-base)| 82.36 | 81.64|
|
100 |
| [distiluse-base-multilingual-cased](https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased) | 78.62 | 77.48|
|
|
|
101 |
|
102 |
|
103 |
## Citation
|
|
|
24 |
type: Pearson_correlation_coefficient
|
25 |
value: xx.xx
|
26 |
---
|
27 |
+
## Description:
|
28 |
+
Sentence-CamemBERT-Large 🇫🇷 is the Embedding Model for French developed by [La Javaness](https://www.lajavaness.com/). It is successfully integrated into our [GEDI](https://www.lajavaness.com/gedi) search platform which allows it to understand the meaning of the text - beyond individual words in queries and documents, offering a powerful semantic search.
|
29 |
|
30 |
+
## Pre-trained sentence embedding models are state-of-the-art of Sentence Embeddings for French.
|
31 |
+
The model is Fine-tuned using pre-trained [facebook/camembert-large](https://huggingface.co/camembert/camembert-large) and
|
32 |
[Siamese BERT-Networks with 'sentences-transformers'](https://www.sbert.net/) on dataset [stsb](https://huggingface.co/datasets/stsb_multi_mt/viewer/fr/train)
|
33 |
|
34 |
|
|
|
92 |
| [dangvantuan/sentence-camembert-large](https://huggingface.co/dangvantuan/sentence-camembert-large)| 88.2 |88.02 | 336M|
|
93 |
| [dangvantuan/sentence-camembert-base](https://huggingface.co/dangvantuan/sentence-camembert-base) | 86.73|86.54 | 110M |
|
94 |
| [distiluse-base-multilingual-cased](https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased) | 79.22 | 79.16|135M |
|
95 |
+
| [GPT-3 (text-davinci-003)](https://platform.openai.com/docs/models) | 85 | NaN|175B |
|
96 |
- On test
|
97 |
|
98 |
|
|
|
101 |
| [dangvantuan/sentence-camembert-large](https://huggingface.co/dangvantuan/sentence-camembert-large)| 85.9 | 85.8|
|
102 |
| [dangvantuan/sentence-camembert-base](https://huggingface.co/dangvantuan/sentence-camembert-base)| 82.36 | 81.64|
|
103 |
| [distiluse-base-multilingual-cased](https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased) | 78.62 | 77.48|
|
104 |
+
| [GPT-3 (text-davinci-003)](https://platform.openai.com/docs/models) | 82 | NaN|175B |
|
105 |
|
106 |
|
107 |
## Citation
|