Closed yaman closed 10 months ago
Hey @yaman. This library intends to maintain parity with the original Python implementation. I recommend model contributions should be made to https://github.com/qdrant/fastembed.
Any new changes there should be reflected here soon.
Thanks @Anush008 for the response. I created an issue at https://github.com/qdrant/fastembed/issues/70
I was working on exporting sentence-transformers/clip-ViT-B-32-multilingual-v1 model to onnx without success. Finally I figured out by manipulating model with torch.onnx. I can contribute onnx model to fastembed-rs with the custom steps of torch.onnx export(python script).
Should I create a pull request?