Skip to content

Conversation

@ferroteo
Copy link
Collaborator

new version which allows to define both model and vocabularies to be used in the app.

1. Added --vocabulary argument
2. Removed duplicates
3. Changed input file to concept_bridge.parquet
4 Embeddings from code only
5. Saves as numpy arrays in folder structure: embeddings/model_name/vocabulary/embeddings.npy
@ferroteo
Copy link
Collaborator Author

Issues:

  • WebApp.py file still needs to be adjusted to work with hugging face
  • WebApp.py will need to run on all availble vocabularies in pre conmputed embedding folder, and not declared ones via argument

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