| { | |
| "backend": "tokenizers", | |
| "bos_token": "<cls>", | |
| "chain_break_token": "|", | |
| "cls_token": "<cls>", | |
| "eos_token": "<eos>", | |
| "extra_special_tokens": [], | |
| "is_local": true, | |
| "local_files_only": false, | |
| "mask_token": "<mask>", | |
| "merges": [], | |
| "model_max_length": 2048, | |
| "model_specific_special_tokens": { | |
| "chain_break_token": "|" | |
| }, | |
| "pad_token": "<pad>", | |
| "tokenizer_class": "EsmcTokenizer", | |
| "unk_token": "<unk>", | |
| "vocab": { | |
| "-": 30, | |
| ".": 29, | |
| "<cls>": 0, | |
| "<eos>": 2, | |
| "<mask>": 32, | |
| "<pad>": 1, | |
| "<unk>": 3, | |
| "A": 5, | |
| "B": 25, | |
| "C": 23, | |
| "D": 13, | |
| "E": 9, | |
| "F": 18, | |
| "G": 6, | |
| "H": 21, | |
| "I": 12, | |
| "K": 15, | |
| "L": 4, | |
| "M": 20, | |
| "N": 17, | |
| "O": 28, | |
| "P": 14, | |
| "Q": 16, | |
| "R": 10, | |
| "S": 8, | |
| "T": 11, | |
| "U": 26, | |
| "V": 7, | |
| "W": 22, | |
| "X": 24, | |
| "Y": 19, | |
| "Z": 27, | |
| "|": 31 | |
| } | |
| } | |