SEBIS/legal_t5_small_trans_fr_en

The legal_t5_small_trans_fr_en model is based on the t5-small model and was trained on a large corpus of parallel text . This variant has about 60 million parameters . 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 . The model could be used for translation of legal texts from French to English in PyTorch . It has a total of approximately 220M parameters . The optimizer used is AdaFactor with inverse square root learning rate schedule for pre-training . An unigram model trained with 88,