36 lines
1.1 KiB
Markdown
36 lines
1.1 KiB
Markdown
|
---
|
||
|
|
pipeline_tag: sentence-similarity
|
||
|
|
tags:
|
||
|
|
- sentence-transformers
|
||
|
|
- feature-extraction
|
||
|
|
- sentence-similarity
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
- fr
|
||
|
|
license: apache-2.0
|
||
|
|
---
|
||
|
|
|
||
|
|
## `semanlink_all_mpnet_base_v2`
|
||
|
|
|
||
|
|
This is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
|
||
|
|
|
||
|
|
`semanlink_all_mpnet_base_v2` has been fine-tuned on the knowledge graph [Semanlink](http://www.semanlink.net/sl/home?lang=fr) via the library [MKB](https://github.com/raphaelsty/mkb) on the link-prediction task. The model is dedicated to the representation of both technical and generic terminology in machine learning, NLP, news.
|
||
|
|
|
||
|
|
## Usage (Sentence-Transformers)
|
||
|
|
|
||
|
|
Using this model becomes easy when you have sentence-transformers installed:
|
||
|
|
|
||
|
|
```
|
||
|
|
pip install -U sentence-transformers
|
||
|
|
```
|
||
|
|
|
||
|
|
Then you can use the model like this:
|
||
|
|
|
||
|
|
```python
|
||
|
|
from sentence_transformers import SentenceTransformer
|
||
|
|
sentences = ["Machine Learning", "Geoffrey Hinton"]
|
||
|
|
|
||
|
|
model = SentenceTransformer('raphaelsty/semanlink_all_mpnet_base_v2')
|
||
|
|
embeddings = model.encode(sentences)
|
||
|
|
print(embeddings)
|
||
|
|
```
|