Add mT5 - Githubissues

Yale-LILY / SummerTime

An open-source text summarization toolkit for non-experts. EMNLP'2021 Demo

https://arxiv.org/abs/2108.12738

Apache License 2.0

264 stars 30 forks source link

Add mT5 #98

Closed haileyschoelkopf closed 2 years ago

haileyschoelkopf commented 2 years ago

add mT5 model (using a checkpoint fine-tuned on the XLSum dataset.)

Ready to merge, but still todo:

possibly adding the rest of the 101 languages that mT5-base was trained on to supported languages, instead of just including the languages in XLSum as supported languages (~45 languages)

niansong1996 commented 2 years ago

Thanks a lot for the PR, Nick!

I haven't got the time to review everything yet, which I will do ASAP.

One thing I noticed is that we don't have the mBART model listed in the Readme.md tables about supported models. Can you add it altogether with mT5 in this PR? Thanks!

haileyschoelkopf commented 2 years ago

Sure, I can add documentation for this and mBART in the PR!

niansong1996 commented 2 years ago

Okay, now that #96 is merged, we should rebase this branch on main or pull from main?

haileyschoelkopf commented 2 years ago

@niansong1996 This PR should be all set for review now!

haileyschoelkopf commented 2 years ago

@niansong1996 should be ready for merge! I have written generic tests for multilingual models (using a Spanish language instance from MLSum) but have not written any specific tests as was done for HMNet. Will do that in another PR though!

niansong1996 commented 2 years ago

Awesome! Merging this PR now.