NVIDIA Deep Learning Examples
NVIDIA Deep Learning Examples
BART PyT checkpoint (Summarization, CNN-DM)
Model
NVIDIA Deep Learning Examples
NVIDIA Deep Learning Examples
BART PyT checkpoint (Summarization, CNN-DM)

BART PyT checkpoint for summarization on CNN-DM dataset

Model Overview

BART is a denoising autoencoder for pretraining sequence-to-sequence models.

Model Architecture

BART uses a standard sequence-to-sequence Transformer architecture with GeLU activations. The base model consists of 6 layers in encoder and decoder, whereas large consists of 12. The architecture has roughly 10% more parameters than BERT.

BART is trained by corrupting documents and then optimizing the reconstruction loss. The pretraining task involves randomly shuffling the order of the original sentences and a novel in-filling scheme, where spans of text are replaced with a single mask token.

Training

This model was trained using script available on NGC and in GitHub repo.

Dataset

The following datasets were used to train this model:

  • CNN/DailyMail - Dataset consisting of news articles (39 sentences on average) paired with multi-sentence summaries.

Performance

Performance numbers for this model are available in NGC.

References

License

This model was trained using open-source software available in Deep Learning Examples repository. For terms of use, please refer to the license of the script and the datasets the model was derived from.

Publisher
NVIDIA Deep Learning Examples
NVIDIA Deep Learning Examples
Latest Version20.11.1_amp
UpdatedApril 4, 2023 UTC
Compressed Size4.14 GB
Labels