| { | |
| "version": "1.0", | |
| "truncation": null, | |
| "padding": null, | |
| "added_tokens": [ | |
| { | |
| "id": 0, | |
| "content": "[BOS]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 5, | |
| "content": "[EOS]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 6, | |
| "content": "[MASK]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 7, | |
| "content": "[PAD]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 8, | |
| "content": "[UNK]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| } | |
| ], | |
| "normalizer": { | |
| "type": "Sequence", | |
| "normalizers": [ | |
| { | |
| "type": "NFKC" | |
| } | |
| ] | |
| }, | |
| "pre_tokenizer": { | |
| "type": "Split", | |
| "pattern": { | |
| "Regex": "." | |
| }, | |
| "behavior": "Isolated", | |
| "invert": false | |
| }, | |
| "post_processor": null, | |
| "decoder": null, | |
| "model": { | |
| "type": "WordLevel", | |
| "vocab": { | |
| "[BOS]": 0, | |
| "A": 1, | |
| "T": 2, | |
| "C": 3, | |
| "G": 4, | |
| "[EOS]": 5, | |
| "[MASK]": 6, | |
| "[PAD]": 7, | |
| "[UNK]": 8 | |
| }, | |
| "unk_token": "[UNK]" | |
| } | |
| } |