Sbert All MiniLM L12 With Pooler

🚀 ONNX convert all-MiniLM-L12-v2

This project focuses on the ONNX conversion of the all-MiniLM-L12-v2 model, enabling efficient sentence and paragraph encoding for tasks such as clustering and semantic search.

🚀 Quick Start

This is a sentence-transformers ONNX model. It maps sentences and 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, while the sentence-transformers exported with the default ONNX config only contains last_hidden_state as output.

📦 Installation

Using this model becomes easy when you have optimum installed. You can install it with the following command:

python -m pip install optimum

💻 Usage Examples

Basic Usage

After installation, you can use the model like this:

from optimum.onnxruntime.modeling_ort import ORTModelForCustomTasks
from transformers import AutoTokenizer

model = ORTModelForCustomTasks.from_pretrained("vamsibanda/sbert-all-MiniLM-L12-with-pooler")
tokenizer = AutoTokenizer.from_pretrained("vamsibanda/sbert-all-MiniLM-L12-with-pooler")
inputs = tokenizer("I love burritos!", return_tensors="pt")
pred = model(**inputs)
embedding = pred['pooler_output']

📄 License

This project is licensed under the Apache 2.0 license.