Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

RuntimeError: "pow" not implemented for 'Half' #18

Open
ivbac opened this issue Apr 19, 2021 · 4 comments
Open

RuntimeError: "pow" not implemented for 'Half' #18

ivbac opened this issue Apr 19, 2021 · 4 comments

Comments

@ivbac
Copy link

ivbac commented Apr 19, 2021

not sure what that means?

@artitw
Copy link
Owner

artitw commented Apr 20, 2021

Where are you getting this error? Please provide more details for reproducibility.

@ivbac
Copy link
Author

ivbac commented Apr 20, 2021

it did not produce that error again after running the code.. but got few messages

from text2text.text_generator import TextGenerator qg = TextGenerator(output_type="question")

and see this message:
**Better speed can be achieved with apex installed from https://www.github.com/artitw/apex.
***** Recover model: qg_model.bin *******

s = 'I ate eggs and waffles this morning'
qg.predict([s])

[('What did I do with eggs and waffles?', 'ate')]

its kind of slow also

@artitw
Copy link
Owner

artitw commented Apr 24, 2021

  1. Have you installed the apex as suggested by the message? There is an example demo notebook that has it working.
  2. Can you provide the specifications for your machine and time how long it takes?

@artitw
Copy link
Owner

artitw commented May 9, 2021

@ivbac have you tried running on GPU?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants