Hugging Face's logo

Xenova
/
bge-m3

Feature Extraction
Transformers.js
ONNX
xlm-roberta
Model card Files
xet
 Community
9

How was expored from m3

#1
by bergum - opened
Discussion
bergum

I'm wondering if you could share how the model was exported to onnx? I see that it has two outputtoken_embeddings and sentence_embedding
Xenova
 Owner

Still a WIP, but it's with this PR.
aapot

Hi @bergum I just wrote code leveraging HF Optimum library to export BGE-M3 to single ONNX model which outputs dense, sparse and colbert vecs all at once. Let me know if you are interested in it
bergum

That would be awesome @aapot !
aapot

@bergum I just published my ONNX model and also needed scripts to export the ONNX model here: https://huggingface.co/aapot/bge-m3-onnx
Let me know if you have any questions!
bergum

Wonderful @aapot !

Sign up or log in to comment