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

add option to support customized elmo embeddings #661

Merged
merged 2 commits into from
Apr 16, 2019

Conversation

GiliGoldin
Copy link
Contributor

@GiliGoldin GiliGoldin commented Apr 13, 2019

I added two optional arguments to ELMoEmbeddings's init function:

  1. options_file
  2. weights_file
    This way a customized ELMO model can be provided by the user for embeddings.
    This is useful for using a self-trained ELMO model or any known ELMO models that are not yet supported by Flair.

@stefan-it stefan-it self-requested a review April 15, 2019 08:22
Copy link
Member

@stefan-it stefan-it left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

flair/embeddings.py Show resolved Hide resolved
@stefan-it
Copy link
Member

Thanks for that PR :) I just left a review ☺️

@alanakbik
Copy link
Collaborator

👍

@alanakbik
Copy link
Collaborator

@GiliGoldin thanks for adding this!
@stefan-it I've merged to the new code formatting style - could you +1 and merge?

@stefan-it
Copy link
Member

👍

@stefan-it stefan-it merged commit dea50fa into flairNLP:master Apr 16, 2019
@alanakbik
Copy link
Collaborator

Thanks!

jonasadigi pushed a commit to adigi-ai/flair that referenced this pull request Dec 7, 2020
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

Successfully merging this pull request may close these issues.

3 participants