← back

PortfolioCollect

https://huggingface.co/facebook/bart-large-cnn

BART is a transformer encoder-encoder (seq2seq) model with a bidirectional (BERT-like) encoder and an autoregressive (GPT-like) decoder. BART is pre-trained by (1) corrupting text with an arbitrary noising function, and (2) learning a model to reconstruct the original text.

curl "http://localhost:8080/screenshot?url=https://arthew0.online/" > /tmp/screenshot_arthew0.online.png