0

Does a model saved to onnx/ tensorRT format format supports adapter models plug just like we can do it in PyTorch or Tensorflow? If there is any proper tutorial or someone can provide details of it, would be appreciated.

I have tried to find in GitHub discussions and other stackoverflow posts, didn't find any concrete answers. There is a PR opened for the same, not closed yet, but not much discusiion.

Sajal
  • 96
  • 1
  • 5

1 Answers1

0

I have tried this also for using adapters with pretrained transformers with torch.jit.trace to get into torchscript. I had no look as the adapter-transformers library has conditionals in the forward methods, meaning its data dependent which is not allowed when tracing a model.

James O'Neill
  • 1
  • As it’s currently written, your answer is unclear. Please [edit] to add additional details that will help others understand how this addresses the question asked. You can find more information on how to write good answers [in the help center](/help/how-to-answer). – Community Aug 27 '23 at 09:38