|
--- |
|
pipeline_tag: sentence-similarity |
|
language: en |
|
license: apache-2.0 |
|
tags: |
|
- sentence-transformers |
|
- feature-extraction |
|
- sentence-similarity |
|
- transformers |
|
- onnx |
|
--- |
|
|
|
# ONNX convert all-MiniLM-L6-v2 |
|
## Conversion of [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L12-v2) |
|
This is a [sentence-transformers](https://www.SBERT.net) ONNX model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search. This custom model takes `last_hidden_state` and `pooler_output` whereas the sentence-transformers exported with default ONNX config only contains `last_hidden_state` as output. |
|
|
|
## Usage (HuggingFace Optimum) |
|
Using this model becomes easy when you have [optimum](https://github.com/huggingface/optimum) installed: |
|
``` |
|
python -m pip install optimum |
|
``` |
|
Then you can use the model like this: |
|
```python |
|
from optimum.onnxruntime.modeling_ort import ORTModelForCustomTasks |
|
|
|
model = ORTModelForCustomTasks.from_pretrained("vamsibanda/sbert-all-MiniLM-L6-with-pooler") |
|
tokenizer = AutoTokenizer.from_pretrained("vamsibanda/sbert-all-MiniLM-L6-with-pooler") |
|
inputs = tokenizer("I love burritos!", return_tensors="pt") |
|
pred = model(**inputs) |
|
embedding = pred['pooler_output'] |
|
``` |
