nka 1.0.2

An example package. Generated with cookiecutter-pylibrary.

Input Sequence Length Transformer models like BERT / RoBERTa / DistilBERT etc. the runtime and the memory requirement grows quadratic with the input length. This limits transformers to inputs of certain lengths. A common value for BERT & Co. are 512 word pieces, which corresponde to about 300-400 words (for English). Longer texts than this are truncated to the first x word pieces.

By default, the provided methods use a limit fo 128 word pieces, longer inputs will be truncated. You can get and set the maximal sequence length like this:

An example package. Generated with cookiecutter-pylibrary.

• Free software: MIT license

Installation

pip install nka

You can also install the in-development version with:

pip install https://github.com/tobibias/neural-keyword-assignment/archive/main.zip

Documentation

https://neural-keyword-assignment.readthedocs.io/

Development

To run all the tests run:

tox

Note, to combine the coverage data from all the tox environments run:

Windows	set PYTEST_ADDOPTS=--cov-append tox
Other	PYTEST_ADDOPTS=--cov-append tox

Changelog

0.0.0 (2022-06-22)

• First release on PyPI.