| { | |
| "version": "1.0", | |
| "truncation": null, | |
| "padding": { | |
| "strategy": "BatchLongest", | |
| "direction": "Right", | |
| "pad_to_multiple_of": null, | |
| "pad_id": 0, | |
| "pad_type_id": 0, | |
| "pad_token": "[PAD]" | |
| }, | |
| "added_tokens": [ | |
| { | |
| "id": 0, | |
| "content": "[PAD]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 1, | |
| "content": "[UNK]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 2, | |
| "content": "[CLS]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 3, | |
| "content": "[SEP]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| } | |
| ], | |
| "normalizer": { | |
| "type": "Sequence", | |
| "normalizers": [ | |
| { | |
| "type": "NFD" | |
| }, | |
| { | |
| "type": "Lowercase" | |
| }, | |
| { | |
| "type": "StripAccents" | |
| } | |
| ] | |
| }, | |
| "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": [ | |
| { | |
| "Sequence": { | |
| "id": "A", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "Sequence": { | |
| "id": "B", | |
| "type_id": 1 | |
| } | |
| } | |
| ], | |
| "special_tokens": { | |
| "[CLS]": { | |
| "id": "[CLS]", | |
| "ids": [ | |
| 2 | |
| ], | |
| "tokens": [ | |
| "[CLS]" | |
| ] | |
| }, | |
| "[SEP]": { | |
| "id": "[SEP]", | |
| "ids": [ | |
| 3 | |
| ], | |
| "tokens": [ | |
| "[SEP]" | |
| ] | |
| } | |
| } | |
| }, | |
| "decoder": null, | |
| "model": { | |
| "type": "WordLevel", | |
| "vocab": { | |
| "[PAD]": 0, | |
| "[UNK]": 1, | |
| "[CLS]": 2, | |
| "[SEP]": 3, | |
| "es": 4, | |
| "un": 5, | |
| "la": 6, | |
| "verdad": 7, | |
| "y": 8, | |
| ",": 9, | |
| "bastante": 10, | |
| "depto": 11, | |
| "pero": 12, | |
| "sobre": 13, | |
| "todo": 14, | |
| "chico": 15, | |
| "oscuro": 16, | |
| "frio": 17, | |
| "comodo": 18, | |
| "tranquilo": 19, | |
| "feo": 20, | |
| "inseguro": 21, | |
| "ruidoso": 22, | |
| "viejo": 23, | |
| "calido": 24, | |
| "humedo": 25, | |
| "lindo": 26, | |
| "luminoso": 27, | |
| "amplio": 28, | |
| "seguro": 29, | |
| "moderno": 30, | |
| "departamento": 31, | |
| "el": 32, | |
| "muy": 33, | |
| "lugar": 34, | |
| "me": 35, | |
| "parecio": 36 | |
| }, | |
| "unk_token": "[UNK]" | |
| } | |
| } |