Seq2Seq Generation Improvements

A sneaky bug was fixed that improves generation and finetuning performance for Bart, Marian, MBart and Pegasus. If you have a trained sequence to sequence model, you may get a nice surprise if you rerun evaluation 🙃

Hugging Face  


Events & TalksEvents & Talks

Have Ideas or Feedback for the Next Issue?

Email We would love your feedback and support!

Hugging Face