SEBIS/legal_t5_small_summ_en

Legal_t5_small_summ_en model is based on the t5-small model . It scales the baseline model of t5 down by using dmodel = 512, dff = 2,048, 8-headed attention, and only 6 layers each in the encoder and decoder . This variant has about 60 million parameters . The model could be used for summarization of legal texts written in English in PyTorch . It was first released in this repository in 2006 . It is a smaller model, which scales the model down to a smaller version of the model t5 . It could be trained on three parallel corpus from jrc-acquis . It has about,