# ALBERT for TensorFlow

This is a fork of the original ALBERT repository that adds package configuration so that it can be easily installed and used. The purpose is to remove the need of cloning the repository and modifying it locally which can be quite dirty for common tasks (e.g. training a new classifier). A lot of code could be shared (e.g. modeling.py, optimization.py) and this fork is exactly for that.

All the credit goes to google-research/albert.

Please refer to the official repository for details on how to use the modules contained in this package. Useful information can also be found in the ALBERT paper.

# Release Notes

• November 5, 2019: Initial version - v1.0.
• November 15, 2019: version 1.1 - v1.1.

## Project details

Uploaded source
Uploaded py3