LoRA
LoRA copied to clipboard
Current implementation can't be converted to ONNX
Please avoid using .T
RuntimeError: Exporting the operator numpy_T to ONNX opset version 12 is not supported. Please open a bug to request ONNX export support for the missing operator.
Thanks :)
Thanks for flagging this! Do you know the best way to fix this?
Replacing it with .transpose should work 👍
Hi talbaumel,
I changed .T to .transpose(0, 1) in a new branch called eval
.
Let me know if this resolves the issue for you!
Perfect, thank you