nreimers's picture
upload
00f9256
|
raw
history blame
1.85 kB
---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
license: apache-2.0
---
# use-cmlm-multilingual
This is a pytorch version of the [universal-sentence-encoder-cmlm/multilingual-base-br](https://tfhub.dev/google/universal-sentence-encoder-cmlm/multilingual-base-br/1) model. It can be used to map 109 languages to a shared vector space. As the model is based [LaBSE](https://huggingface.co/sentence-transformers/LaBSE), it perform quite comparable on downstream tasks.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/use-cmlm-multilingual')
embeddings = model.encode(sentences)
print(embeddings)
```
## Evaluation Results
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)
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
(2): Normalize()
)
```
## Citing & Authors
Have a look at [universal-sentence-encoder-cmlm/multilingual-base-br](https://tfhub.dev/google/universal-sentence-encoder-cmlm/multilingual-base-br/1) for the respective publication that describes this model.