Add tokenizer files
7fe9223 verified | { |
| "version": "1.0", |
| "truncation": null, |
| "padding": null, |
| "added_tokens": [ |
| { |
| "id": 0, |
| "content": "_", |
| "single_word": false, |
| "lstrip": false, |
| "rstrip": false, |
| "normalized": false, |
| "special": true |
| }, |
| { |
| "id": 1, |
| "content": "[PAD]", |
| "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 |
| }, |
| { |
| "id": 3, |
| "content": "[BOS]", |
| "single_word": false, |
| "lstrip": false, |
| "rstrip": false, |
| "normalized": false, |
| "special": true |
| }, |
| { |
| "id": 4, |
| "content": "[EOS]", |
| "single_word": false, |
| "lstrip": false, |
| "rstrip": false, |
| "normalized": false, |
| "special": true |
| } |
| ], |
| "normalizer": { |
| "type": "Sequence", |
| "normalizers": [ |
| { |
| "type": "NFD" |
| }, |
| { |
| "type": "StripAccents" |
| }, |
| { |
| "type": "Lowercase" |
| } |
| ] |
| }, |
| "pre_tokenizer": { |
| "type": "Whitespace" |
| }, |
| "post_processor": null, |
| "decoder": null, |
| "model": { |
| "type": "WordLevel", |
| "vocab": { |
| "_": 0, |
| "[PAD]": 1, |
| "[UNK]": 2, |
| "[BOS]": 3, |
| "[EOS]": 4, |
| "a": 5, |
| "b": 6, |
| "c": 7, |
| "d": 8, |
| "e": 9, |
| "f": 10, |
| "g": 11, |
| "h": 12, |
| "i": 13, |
| "j": 14, |
| "k": 15, |
| "l": 16, |
| "m": 17, |
| "n": 18, |
| "o": 19, |
| "p": 20, |
| "q": 21, |
| "r": 22, |
| "s": 23, |
| "t": 24, |
| "u": 25, |
| "v": 26, |
| "w": 27, |
| "x": 28, |
| "y": 29, |
| "z": 30, |
| "0": 31, |
| "1": 32, |
| "2": 33, |
| "3": 34, |
| "4": 35, |
| "5": 36, |
| "6": 37, |
| "7": 38, |
| "8": 39, |
| "9": 40, |
| "10": 41, |
| "11": 42, |
| "12": 43, |
| "13": 44, |
| "14": 45, |
| "15": 46, |
| "16": 47, |
| "|": 48, |
| "?": 49, |
| "(": 50, |
| ")": 51 |
| }, |
| "unk_token": "[UNK]" |
| } |
| } |
