JulesBelveze
commited on
Commit
•
69cf90c
1
Parent(s):
9098fb6
Delete README.md
Browse files
README.md
DELETED
@@ -1,56 +0,0 @@
|
|
1 |
-
---
|
2 |
-
pipeline_tag: sentence-similarity
|
3 |
-
tags:
|
4 |
-
- sentence-transformers
|
5 |
-
- feature-extraction
|
6 |
-
- sentence-similarity
|
7 |
-
- transformers
|
8 |
-
license: apache-2.0
|
9 |
-
---
|
10 |
-
|
11 |
-
# LaBSE
|
12 |
-
This is a port of the [LaBSE](https://tfhub.dev/google/LaBSE/1) model to PyTorch. It can be used to map 109 languages to a shared vector space.
|
13 |
-
|
14 |
-
|
15 |
-
## Usage (Sentence-Transformers)
|
16 |
-
|
17 |
-
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
|
18 |
-
|
19 |
-
```
|
20 |
-
pip install -U sentence-transformers
|
21 |
-
```
|
22 |
-
|
23 |
-
Then you can use the model like this:
|
24 |
-
|
25 |
-
```python
|
26 |
-
from sentence_transformers import SentenceTransformer
|
27 |
-
sentences = ["This is an example sentence", "Each sentence is converted"]
|
28 |
-
|
29 |
-
model = SentenceTransformer('sentence-transformers/LaBSE')
|
30 |
-
embeddings = model.encode(sentences)
|
31 |
-
print(embeddings)
|
32 |
-
```
|
33 |
-
|
34 |
-
|
35 |
-
|
36 |
-
## Evaluation Results
|
37 |
-
|
38 |
-
|
39 |
-
|
40 |
-
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/LaBSE)
|
41 |
-
|
42 |
-
|
43 |
-
|
44 |
-
## Full Model Architecture
|
45 |
-
```
|
46 |
-
SentenceTransformer(
|
47 |
-
(0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel
|
48 |
-
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
|
49 |
-
(2): Dense({'in_features': 768, 'out_features': 768, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
|
50 |
-
(3): Normalize()
|
51 |
-
)
|
52 |
-
```
|
53 |
-
|
54 |
-
## Citing & Authors
|
55 |
-
|
56 |
-
Have a look at [LaBSE](https://tfhub.dev/google/LaBSE/1) for the respective publication that describes LaBSE.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|