| { | |
| "seq_len": 51, | |
| "vocab": { | |
| "_": 0, | |
| "A": 1, | |
| "C": 2, | |
| "D": 3, | |
| "E": 4, | |
| "F": 5, | |
| "G": 6, | |
| "H": 7, | |
| "I": 8, | |
| "K": 9, | |
| "L": 10, | |
| "M": 11, | |
| "N": 12, | |
| "P": 13, | |
| "Q": 14, | |
| "R": 15, | |
| "S": 16, | |
| "T": 17, | |
| "V": 18, | |
| "W": 19, | |
| "Y": 20, | |
| "X": 21 | |
| }, | |
| "cleaning": { | |
| "padding_token": "_", | |
| "unknown_token": "X", | |
| "keep_existing_x": true, | |
| "map_non_standard_to": "X", | |
| "pad_truncate_to": 51 | |
| } | |
| } | |