Upload model.onnx
#19
by
tkelmATlegends
- opened
Adding the ONNX version of the model from this repo.
created with this command:
python3 -m transformers.onnx --model='sentence-transformers/all-MiniLM-L6-v2'
tkelmATlegends
changed pull request status to
closed
tkelmATlegends
changed pull request status to
open
@tkelmATlegends Does this add any quantization? If yes, how to disable quantization? can this be used with GPU and CPU?