| { | |
| "version": "1.0", | |
| "truncation": null, | |
| "padding": null, | |
| "added_tokens": [], | |
| "normalizer": null, | |
| "pre_tokenizer": { | |
| "type": "BertPreTokenizer" | |
| }, | |
| "post_processor": { | |
| "type": "BertPostProcessor", | |
| "sep": { | |
| "type": "SpecialToken", | |
| "id": 102, | |
| "piece": "[SEP]" | |
| }, | |
| "cls": { | |
| "type": "SpecialToken", | |
| "id": 101, | |
| "piece": "[CLS]" | |
| } | |
| }, | |
| "decoder": null, | |
| "model": { | |
| "type": "BertWordPiece", | |
| "vocab": { | |
| "[PAD]": 0, | |
| "[UNK]": 1, | |
| "[CLS]": 101, | |
| "[SEP]": 102, | |
| "[MASK]": 103, | |
| "other": 104, | |
| "words": 105 | |
| // Incluye todas las palabras del vocabulario aquí | |
| }, | |
| "unk_token": "[UNK]" | |
| } | |
| } | |