{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 0, "special": true, "content": "[UNK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false }, { "id": 1, "special": true, "content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false }, { "id": 2, "special": true, "content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false }, { "id": 3, "special": true, "content": "[PAD]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false }, { "id": 4, "special": true, "content": "[MASK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false } ], "normalizer": null, "pre_tokenizer": { "type": "Whitespace" }, "post_processor": { "type": "TemplateProcessing", "single": [ { "SpecialToken": { "id": "[CLS]", "type_id": 0 } }, { "Sequence": { "id": "A", "type_id": 0 } }, { "SpecialToken": { "id": "[SEP]", "type_id": 0 } } ], "pair": [ { "SpecialToken": { "id": "[CLS]", "type_id": 0 } }, { "Sequence": { "id": "A", "type_id": 0 } }, { "SpecialToken": { "id": "[SEP]", "type_id": 0 } }, { "Sequence": { "id": "B", "type_id": 1 } }, { "SpecialToken": { "id": "[SEP]", "type_id": 1 } } ], "special_tokens": { "[CLS]": { "id": "[CLS]", "ids": [ 1 ], "tokens": [ "[CLS]" ] }, "[SEP]": { "id": "[SEP]", "ids": [ 2 ], "tokens": [ "[SEP]" ] } } }, "decoder": null, "model": { "type": "BPE", "dropout": null, "unk_token": "[UNK]", "continuing_subword_prefix": null, "end_of_word_suffix": null, "fuse_unk": false, "vocab": { "[UNK]": 0, "[CLS]": 1, "[SEP]": 2, "[PAD]": 3, "[MASK]": 4, "A": 5, "C": 6, "G": 7, "T": 8 }, "merges": [ ] } }