|
|
--- |
|
|
tags: |
|
|
- sentence-similarity |
|
|
inference: false |
|
|
license: cc-by-sa-3.0 |
|
|
language: en |
|
|
library_name: staticvectors |
|
|
--- |
|
|
|
|
|
# FastText StaticVectors model |
|
|
|
|
|
This model is an export of these [FastText English Vectors](https://fasttext.cc/docs/en/english-vectors.html) (_wiki-news-300d-1M-subword.vec.zip_) for [`staticvectors`](https://github.com/neuml/staticvectors). `staticvectors` enables running inference in Python with NumPy. This helps it maintain solid runtime performance. |
|
|
|
|
|
## Usage with StaticVectors |
|
|
|
|
|
```python |
|
|
from staticvectors import StaticVectors |
|
|
|
|
|
model = StaticVectors("neuml/fasttext") |
|
|
model.embeddings(["word"]) |
|
|
``` |
|
|
|
|
|
Given that pre-trained embeddings models can get quite large, there is also a SQLite version that lazily loads vectors. |
|
|
|
|
|
```python |
|
|
from staticvectors import StaticVectors |
|
|
|
|
|
model = StaticVectors("neuml/fasttext/model.sqlite") |
|
|
model.embeddings(["word"]) |
|
|
``` |
|
|
|
