SEBIS/legal_t5_small_trans_de_fr

The legal_t5_small_trans_de_fr model is based on the t5-small model and was trained on a large corpus of parallel text . 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 translation of legal texts from Deustch to French. It has a total of approximately 220M parameters . The model is trained on three parallel corpus from jrc-acquis, europarl and dcep. The optimizer used is Ada,