| { | |
| "version": "1.0", | |
| "truncation": null, | |
| "padding": null, | |
| "added_tokens": [ | |
| { | |
| "id": 0, | |
| "content": "[PAD]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 1, | |
| "content": "[MASK]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 2, | |
| "content": "[UNK]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| } | |
| ], | |
| "normalizer": { | |
| "type": "Lowercase" | |
| }, | |
| "pre_tokenizer": { | |
| "type": "Whitespace" | |
| }, | |
| "post_processor": null, | |
| "decoder": null, | |
| "model": { | |
| "type": "BPE", | |
| "dropout": null, | |
| "unk_token": "[UNK]", | |
| "continuing_subword_prefix": null, | |
| "end_of_word_suffix": null, | |
| "fuse_unk": false, | |
| "vocab": { | |
| "[PAD]": 0, | |
| "[MASK]": 1, | |
| "[UNK]": 2, | |
| "a": 3, | |
| "c": 4, | |
| "g": 5, | |
| "t": 6 | |
| }, | |
| "merges": [] | |
| } | |
| } |