Upload tokenizer
a9826eb verified | { |
| "version": "1.0", |
| "truncation": null, |
| "padding": null, |
| "added_tokens": [ |
| { |
| "id": 24, |
| "content": "[UNK]", |
| "single_word": false, |
| "lstrip": false, |
| "rstrip": false, |
| "normalized": false, |
| "special": true |
| }, |
| { |
| "id": 25, |
| "content": "[PAD]", |
| "single_word": false, |
| "lstrip": false, |
| "rstrip": false, |
| "normalized": false, |
| "special": true |
| }, |
| { |
| "id": 26, |
| "content": "[CLS]", |
| "single_word": false, |
| "lstrip": false, |
| "rstrip": false, |
| "normalized": false, |
| "special": true |
| }, |
| { |
| "id": 27, |
| "content": "[SEP]", |
| "single_word": false, |
| "lstrip": false, |
| "rstrip": false, |
| "normalized": false, |
| "special": true |
| }, |
| { |
| "id": 28, |
| "content": "[MASK]", |
| "single_word": false, |
| "lstrip": false, |
| "rstrip": false, |
| "normalized": false, |
| "special": true |
| } |
| ], |
| "normalizer": null, |
| "pre_tokenizer": { |
| "type": "Split", |
| "pattern": { |
| "String": "" |
| }, |
| "behavior": "Isolated", |
| "invert": false |
| }, |
| "post_processor": null, |
| "decoder": null, |
| "model": { |
| "type": "WordLevel", |
| "vocab": { |
| "A": 0, |
| "R": 1, |
| "N": 2, |
| "D": 3, |
| "C": 4, |
| "Q": 5, |
| "E": 6, |
| "G": 7, |
| "H": 8, |
| "I": 9, |
| "L": 10, |
| "K": 11, |
| "M": 12, |
| "F": 13, |
| "P": 14, |
| "S": 15, |
| "T": 16, |
| "W": 17, |
| "Y": 18, |
| "V": 19, |
| "B": 20, |
| "Z": 21, |
| "X": 22, |
| "-": 23, |
| "[UNK]": 24, |
| "[PAD]": 25, |
| "[CLS]": 26, |
| "[SEP]": 27, |
| "[MASK]": 28 |
| }, |
| "unk_token": "[UNK]" |
| } |
| } |
