potion-retrieval-32m-onnx

potion-retrieval-32m_onnx Model Card

This is an ONNX export of the minishlab/potion-retrieval-32m Model2Vec model, produced with the ONNX runtime. Model2Vec models use static embeddings, allowing text embeddings to be computed orders of magnitude faster on both GPU and CPU. This ONNX export lets you run the model with onnxruntime or transformers.js, without depending on the model2vec package.

Usage

Using ONNX Runtime

import onnxruntime as ort
from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("potion-retrieval-32m_onnx")
session = ort.InferenceSession("model.onnx")

encodings = tokenizer(["Example sentence"], padding=True, return_tensors="np")
embeddings = session.run(None, dict(encodings))[0]

Using the original Model2Vec model

If you don't need the ONNX runtime, you can load the original model with the Model2Vec library instead:

from model2vec import StaticModel

model = StaticModel.from_pretrained("minishlab/potion-retrieval-32m")
embeddings = model.encode(["Example sentence"])

Additional Resources

• Model2Vec Repo
• Model2Vec Base Models
• Model2Vec Results
• Model2Vec Docs

Library Authors

Model2Vec was developed by the Minish Lab team consisting of Stephan Tulkens and Thomas van Dongen.

Citation

Please cite the Model2Vec repository if you use this model in your work.

@software{minishlab2024model2vec,
  author       = {Stephan Tulkens and {van Dongen}, Thomas},
  title        = {Model2Vec: Fast State-of-the-Art Static Embeddings},
  year         = {2024},
  publisher    = {Zenodo},
  doi          = {10.5281/zenodo.17270888},
  url          = {https://github.com/MinishLab/model2vec},
  license      = {MIT}
}