NGC Catalog
CLASSIC
Welcome Guest
Models
BART PyT checkpoint (Summarization, XSum)

BART PyT checkpoint (Summarization, XSum)

For downloads and more information, please view on a desktop device.
Logo for BART PyT checkpoint (Summarization, XSum)
Description
BART PyT checkpoint for summarization on XSum dataset
Publisher
NVIDIA Deep Learning Examples
Latest Version
20.11.0_amp
Modified
April 4, 2023
Size
4.14 GB

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:

  • Extreme Summarization - Dataset consisting of 226,711 Wayback archived BBC articles ranging over almost a decade (2010 to 2017) and covering a wide variety of domains (e.g., News, Politics, Sports, Weather, Business, Technology, Science, Health, Family, Education, Entertainment and Arts).

Performance

Performance numbers for this model are available in NGC.

References

  • Original paper
  • NVIDIA model implementation in NGC
  • NVIDIA model implementation on GitHub

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.