| { |
| "version": "1.0", |
| "truncation": null, |
| "padding": null, |
| "added_tokens": [ |
| { |
| "id": 0, |
| "content": "<unk>", |
| "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": "<bos>", |
| "single_word": false, |
| "lstrip": false, |
| "rstrip": false, |
| "normalized": false, |
| "special": true |
| }, |
| { |
| "id": 3, |
| "content": "<eos>", |
| "single_word": false, |
| "lstrip": false, |
| "rstrip": false, |
| "normalized": false, |
| "special": true |
| } |
| ], |
| "normalizer": null, |
| "pre_tokenizer": { |
| "type": "Whitespace" |
| }, |
| "post_processor": { |
| "type": "TemplateProcessing", |
| "single": [ |
| { |
| "Sequence": { |
| "id": "A", |
| "type_id": 0 |
| } |
| } |
| ], |
| "pair": [ |
| { |
| "Sequence": { |
| "id": "A", |
| "type_id": 0 |
| } |
| }, |
| { |
| "Sequence": { |
| "id": "B", |
| "type_id": 1 |
| } |
| } |
| ], |
| "special_tokens": {} |
| }, |
| "decoder": null, |
| "model": { |
| "type": "BPE", |
| "dropout": null, |
| "unk_token": null, |
| "continuing_subword_prefix": null, |
| "end_of_word_suffix": null, |
| "fuse_unk": false, |
| "byte_fallback": false, |
| "ignore_merges": false, |
| "vocab": { |
| "<unk>": 0, |
| "<pad>": 1, |
| "<bos>": 2, |
| "<eos>": 3, |
| ",": 4, |
| ".": 5, |
| "A": 6, |
| "B": 7, |
| "G": 8, |
| "H": 9, |
| "K": 10, |
| "Y": 11, |
| "a": 12, |
| "b": 13, |
| "c": 14, |
| "d": 15, |
| "e": 16, |
| "f": 17, |
| "g": 18, |
| "h": 19, |
| "i": 20, |
| "j": 21, |
| "k": 22, |
| "l": 23, |
| "m": 24, |
| "n": 25, |
| "o": 26, |
| "p": 27, |
| "r": 28, |
| "s": 29, |
| "t": 30, |
| "u": 31, |
| "v": 32, |
| "y": 33, |
| "z": 34, |
| "Ö": 35, |
| "â": 36, |
| "ç": 37, |
| "ö": 38, |
| "ü": 39, |
| "ğ": 40, |
| "İ": 41, |
| "ı": 42, |
| "Ş": 43, |
| "ş": 44, |
| "’": 45, |
| "ar": 46, |
| "en": 47, |
| "er": 48, |
| "im": 49, |
| "ir": 50, |
| "an": 51, |
| "du": 52, |
| "dı": 53, |
| "in": 54, |
| "la": 55, |
| "sa": 56, |
| "ün": 57, |
| "bir": 58, |
| "da": 59, |
| "de": 60, |
| "ek": 61, |
| "et": 62, |
| "li": 63 |
| }, |
| "merges": [ |
| [ |
| "a", |
| "r" |
| ], |
| [ |
| "e", |
| "n" |
| ], |
| [ |
| "e", |
| "r" |
| ], |
| [ |
| "i", |
| "m" |
| ], |
| [ |
| "i", |
| "r" |
| ], |
| [ |
| "a", |
| "n" |
| ], |
| [ |
| "d", |
| "u" |
| ], |
| [ |
| "d", |
| "ı" |
| ], |
| [ |
| "i", |
| "n" |
| ], |
| [ |
| "l", |
| "a" |
| ], |
| [ |
| "s", |
| "a" |
| ], |
| [ |
| "ü", |
| "n" |
| ], |
| [ |
| "b", |
| "ir" |
| ], |
| [ |
| "d", |
| "a" |
| ], |
| [ |
| "d", |
| "e" |
| ], |
| [ |
| "e", |
| "k" |
| ], |
| [ |
| "e", |
| "t" |
| ], |
| [ |
| "l", |
| "i" |
| ] |
| ] |
| } |
| } |
