Skip to content

henryzxu/bert-qa-demo

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

24 Commits
 
 
 
 
 
 

Repository files navigation

Interactive Q&A Demo for BERT

Usage

pip install -r requirements.txt    
export FLASK_APP=app/server.py  
flask run

Input priority is given to text-based prompts.

Screenshots

Home Page

home

Results

results

Issues

  • Removing files via the Dropzone UI is currently not supported by the server. For now, all session uploads are cleared upon successful in-memory storage of the latest file-based prompt.

Credits

Credit to Hugging Face for their PyTorch implementation of BERT, which I modified to streamline inference and extraction of additional prediction data.

About

Interactive demo for BERT Q&A.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published