RATransformer - make a transformer model learn implicit relations passed in the input

Project description

RATransformers 🐭

⚠👷‍♀👷‍♂ This package is WIP. Currently we only support the T5 model. Feel free to contribute with PRs!️👷‍♂👷‍♀⚠

RATransformers, short for Relation-Aware Transformers, is a package built on top of transformers that enables the training/fine-tuning of multiple models with some extra relation-aware weights. These extra weights enable the model to encode explicit relations between different parts of the input data.

Project details

Release history Release notifications | RSS feed

1.3.2

Dec 14, 2022

1.3.1

Dec 14, 2022

1.3.0

Dec 13, 2022

1.2.1

Dec 12, 2022

1.2.0

Dec 12, 2022

1.1.0

Dec 12, 2022

1.0.0

Dec 11, 2022

0.1.1

Mar 11, 2022

0.1.0

Feb 15, 2022

This version

0.0.1

Feb 15, 2022

0.0.0

Feb 15, 2022

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ratransformers-0.0.1.tar.gz (9.3 kB view hashes)

Uploaded Feb 15, 2022 Source

Built Distribution

ratransformers-0.0.1-py3-none-any.whl (12.6 kB view hashes)

Uploaded Feb 15, 2022 Python 3

Hashes for ratransformers-0.0.1.tar.gz

Hashes for ratransformers-0.0.1.tar.gz
Algorithm	Hash digest
SHA256	`36abb517d2b89ebca0fb45ffee0ea406295b70e5a848622c17fba1e9598d0076`
MD5	`21be1a25bed363fbcfb62ceea1157155`
BLAKE2b-256	`dce25f5075bc39a42a75beafb1bbefdb3aca7716005a1a57e65d5ea169070619`

Hashes for ratransformers-0.0.1-py3-none-any.whl

Hashes for ratransformers-0.0.1-py3-none-any.whl
Algorithm	Hash digest
SHA256	`2d5be34dd2574698d778688137960da25ba591f4bbf59e73be93b4c9d08676d3`
MD5	`752c1de60e643cf0bf3330b72c430220`
BLAKE2b-256	`a616a3b8449d4902f8270e241c587da7b7c3c6e98c3e96747208522d7804c346`