rTorch: Loading a model trained in PyTorch to R

I'm hoping to load a model trained in Python using PyTorch to R for deployment in a Shiny app. I was wondering if it would be possible to use rTorch to do this, as I don't see any existing threads/reports of this? The model is saved as a .pth file. Additionally, I'm receiving the following error upon trying to load rTorch after following the instructions on the "Installation" heading: https://github.com/f0nzie/rTorch

>> library(rTorch)
    Error: package or namespace load failed for ‘rTorch’ in get(method, envir = envir):
    lazy-load database '/Library/Frameworks/R.framework/Versions/3.6/Resources/library/rTorch/R/rTorch.rdb' is corrupt
    In addition: Warning message:
    In get(method, envir = envir) : internal error -3 in R_decompress1

Any assistance is much appreciated.

Thank you