Utils to run multiple choice question answering with huggingface transformers
Project description
mc_transformers
Code to run experiments over Multiple Choice QA with huggingface/transformers. A big part of the code comes from [huggingface/transformers](https://huggingface.co/transformers/), so its license may apply (Apache v2).
## Code * utils_mc.py: Contains processors specific to each MC QA collection (RACE, SWAG, EntranceExams…) * run_mc_trainer.py: Code to train/eval/test models over any collection with transfomers
## Why As I experiment with more MC collection and training modes (i.e.: tpu), support for more collections or more models is required. Instead of forking the whole transformers library I do it here.
Credits
This package was created with Cookiecutter and the audreyr/cookiecutter-pypackage project template.
History
0.1.0 (2020-07-23)
First release on PyPI.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for mc_transformers-0.1.3-py2.py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 0cff02539eba54f5c8d03a31e727e0504e4e8b5f3dbb064b8dd6d6fe00f60610 |
|
MD5 | b0b4640491334acee83ef78ef7556136 |
|
BLAKE2b-256 | 755777758e4422bbf89ccd6babf7da607acbb75a099c03f3904b36b649f12ce9 |