# Sequence-to-sequence pre-training

BARTpho is the first pre-trained sequence-to-sequence model for Vietnamese, including syllable and word versions, suitable for generative natural language processing tasks.

BARThez is a French sequence-to-sequence pre-trained model based on the BART architecture, particularly suitable for generative tasks such as abstractive summarization.

BARTpho is the first large-scale monolingual sequence-to-sequence pre-trained model for Vietnamese, based on the BART architecture, particularly suitable for generative natural language processing tasks.