onnx-models/paraphrase-multilingual-mpnet-base-v2-onnx
By onnx-models · ↓ 5 · ♥ 0 · Updated 2024-07-27
What's in this repo
This page lists the files in onnx-models/paraphrase-multilingual-mpnet-base-v2-onnx, including model.onnx.
- 1 ONNX models (.onnx files)
- 8 files, including 4 .json, 1 .md, 1 .onnx, 1 .model
- Last updated 2024-07-27
ONNX files
| File | Size | Download |
|---|---|---|
| model.onnx | — | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
onnx-models/paraphrase-multilingual-mpnet-base-v2-onnx
This is the ONNX-ported version of the sentence-transformers/paraphrase-multilingual-mpnet-base-v2 for generating text embeddings.
Model details
- Embedding dimension: 768
- Max sequence length: 128
- File size on disk: 1.03 GB
- Modules incorporated in the onnx: Transformer, Pooling
Usage
Using this model becomes easy when you have light-embed installed:
pip install -U light-embed
Then you can use the model by specifying the original model name like this:
from light_embed import TextEmbedding
sentences = [
"This is an example sentence",
"Each sentence is converted"
]
model = TextEmbedding('sentence-transformers/paraphrase-multilingual-mpnet-base-v2')
embeddings = model.encode(sentences)
print(embeddings)
or by specifying the onnx model name like this:
from light_embed import TextEmbedding
sentences = [
"This is an example sentence",
"Each sentence is converted"
]
model = TextEmbedding('onnx-models/paraphrase-multilingual-mpnet-base-v2-onnx')
embeddings = model.encode(sentences)
print(embeddings)
Citing & Authors
Binh Nguyen / binhcode25@gmail.com
Model info
Created: 2024-07-27
Updated: 2024-07-27
View on Hugging Face