Rostlab/prot_t5_xl_bfd

The ProtT5-XL-BFD model is based on the t5-3b model and was pretrained on a large corpus of protein sequences in a self-supervised fashion . This model is trained on uppercase amino acids: it only works with capital letter amino acids . The model could be used for protein feature extraction or to be fine-tuned on downstream tasks . For feature extraction, its better to use the feature extracted from the encoder not from the decoder . The masking probability is consistent with the original T5 training by randomly masking 15% of the amino acids in the input . The rare amino acids "U,Z,O,B",