byeongal/bart-large

1---2license: mit3thumbnail: https://huggingface.co/front/thumbnails/facebook.png4language: en5tags:6  - bart7---8# BART base model for Teachable NLP9 10- This model forked from [bart-base](https://huggingface.co/facebook/bart-base) for fine tune [Teachable NLP](https://ainize.ai/teachable-nlp).11 12The Bart model was proposed by Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov and Luke Zettlemoyer on 29 Oct, 2019. According to the abstract,13 14Bart uses a standard seq2seq/machine translation architecture with a bidirectional encoder (like BERT) and a left-to-right decoder (like GPT).15 16The 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.17 18BART is particularly effective when fine tuned for text generation but also works well for comprehension tasks. It matches the performance of RoBERTa with comparable training resources on GLUE and SQuAD, achieves new state-of-the-art results on a range of abstractive dialogue, question answering, and summarization tasks, with gains of up to 6 ROUGE.19 20The Authors’ code can be found here:21https://github.com/pytorch/fairseq/tree/master/examples/bart22