| { |
| "version": "1.0", |
| "truncation": null, |
| "padding": null, |
| "added_tokens": [ |
| { |
| "id": 0, |
| "content": "<pad>", |
| "single_word": false, |
| "lstrip": false, |
| "rstrip": false, |
| "normalized": false, |
| "special": true |
| }, |
| { |
| "id": 1, |
| "content": "<s>", |
| "single_word": false, |
| "lstrip": false, |
| "rstrip": false, |
| "normalized": false, |
| "special": true |
| }, |
| { |
| "id": 2, |
| "content": "</s>", |
| "single_word": false, |
| "lstrip": false, |
| "rstrip": false, |
| "normalized": false, |
| "special": true |
| }, |
| { |
| "id": 3, |
| "content": "<unk>", |
| "single_word": false, |
| "lstrip": false, |
| "rstrip": false, |
| "normalized": false, |
| "special": true |
| } |
| ], |
| "normalizer": null, |
| "pre_tokenizer": { |
| "type": "ByteLevel", |
| "add_prefix_space": false, |
| "trim_offsets": true, |
| "use_regex": true |
| }, |
| "post_processor": null, |
| "decoder": { |
| "type": "ByteLevel", |
| "add_prefix_space": true, |
| "trim_offsets": true, |
| "use_regex": true |
| }, |
| "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": { |
| "<pad>": 0, |
| "<s>": 1, |
| "</s>": 2, |
| "<unk>": 3, |
| "H": 4, |
| "T": 5, |
| "a": 6, |
| "b": 7, |
| "c": 8, |
| "d": 9, |
| "e": 10, |
| "f": 11, |
| "g": 12, |
| "h": 13, |
| "i": 14, |
| "j": 15, |
| "k": 16, |
| "l": 17, |
| "m": 18, |
| "n": 19, |
| "o": 20, |
| "p": 21, |
| "q": 22, |
| "r": 23, |
| "s": 24, |
| "t": 25, |
| "u": 26, |
| "v": 27, |
| "w": 28, |
| "x": 29, |
| "y": 30, |
| "z": 31, |
| "Ċ": 32, |
| "Ġ": 33, |
| "Ġt": 34, |
| "he": 35, |
| "Ġthe": 36, |
| "el": 37, |
| "er": 38, |
| "fo": 39, |
| "is": 40, |
| "Ġo": 41, |
| "Ġfo": 42, |
| "Hel": 43, |
| "The": 44, |
| "az": 45, |
| "br": 46, |
| "ck": 47, |
| "do": 48, |
| "del": 49, |
| "en": 50, |
| "es": 51, |
| "his": 52, |
| "iz": 53, |
| "ick": 54, |
| "ju": 55, |
| "ken": 56, |
| "ld": 57, |
| "lo": 58, |
| "laz": 59, |
| "mo": 60, |
| "mp": 61, |
| "or": 62, |
| "ow": 63, |
| "oken": 64, |
| "qu": 65, |
| "ver": 66, |
| "wor": 67, |
| "Ġa": 68, |
| "Ġis": 69, |
| "Ġbr": 70, |
| "Ġdo": 71, |
| "Ġju": 72, |
| "Ġlaz": 73, |
| "Ġmo": 74, |
| "Ġqu": 75, |
| "Ġwor": 76, |
| "Ġtes": 77, |
| "Ġthis": 78, |
| "Ġtoken": 79, |
| "Ġof": 80, |
| "Ġover": 81, |
| "Ġfor": 82, |
| "Ġfox": 83, |
| "Hello": 84, |
| "izer": 85, |
| "mps": 86, |
| "own": 87, |
| "Ġbrown": 88, |
| "Ġdog": 89, |
| "Ġjumps": 90, |
| "Ġlazy": 91, |
| "Ġmodel": 92, |
| "Ġquick": 93, |
| "Ġworld": 94, |
| "Ġtest": 95, |
| "Ġtokenizer": 96 |
| }, |
| "merges": [ |
| [ |
| "Ġ", |
| "t" |
| ], |
| [ |
| "h", |
| "e" |
| ], |
| [ |
| "Ġt", |
| "he" |
| ], |
| [ |
| "e", |
| "l" |
| ], |
| [ |
| "e", |
| "r" |
| ], |
| [ |
| "f", |
| "o" |
| ], |
| [ |
| "i", |
| "s" |
| ], |
| [ |
| "Ġ", |
| "o" |
| ], |
| [ |
| "Ġ", |
| "fo" |
| ], |
| [ |
| "H", |
| "el" |
| ], |
| [ |
| "T", |
| "he" |
| ], |
| [ |
| "a", |
| "z" |
| ], |
| [ |
| "b", |
| "r" |
| ], |
| [ |
| "c", |
| "k" |
| ], |
| [ |
| "d", |
| "o" |
| ], |
| [ |
| "d", |
| "el" |
| ], |
| [ |
| "e", |
| "n" |
| ], |
| [ |
| "e", |
| "s" |
| ], |
| [ |
| "h", |
| "is" |
| ], |
| [ |
| "i", |
| "z" |
| ], |
| [ |
| "i", |
| "ck" |
| ], |
| [ |
| "j", |
| "u" |
| ], |
| [ |
| "k", |
| "en" |
| ], |
| [ |
| "l", |
| "d" |
| ], |
| [ |
| "l", |
| "o" |
| ], |
| [ |
| "l", |
| "az" |
| ], |
| [ |
| "m", |
| "o" |
| ], |
| [ |
| "m", |
| "p" |
| ], |
| [ |
| "o", |
| "r" |
| ], |
| [ |
| "o", |
| "w" |
| ], |
| [ |
| "o", |
| "ken" |
| ], |
| [ |
| "q", |
| "u" |
| ], |
| [ |
| "v", |
| "er" |
| ], |
| [ |
| "w", |
| "or" |
| ], |
| [ |
| "Ġ", |
| "a" |
| ], |
| [ |
| "Ġ", |
| "is" |
| ], |
| [ |
| "Ġ", |
| "br" |
| ], |
| [ |
| "Ġ", |
| "do" |
| ], |
| [ |
| "Ġ", |
| "ju" |
| ], |
| [ |
| "Ġ", |
| "laz" |
| ], |
| [ |
| "Ġ", |
| "mo" |
| ], |
| [ |
| "Ġ", |
| "qu" |
| ], |
| [ |
| "Ġ", |
| "wor" |
| ], |
| [ |
| "Ġt", |
| "es" |
| ], |
| [ |
| "Ġt", |
| "his" |
| ], |
| [ |
| "Ġt", |
| "oken" |
| ], |
| [ |
| "Ġo", |
| "f" |
| ], |
| [ |
| "Ġo", |
| "ver" |
| ], |
| [ |
| "Ġfo", |
| "r" |
| ], |
| [ |
| "Ġfo", |
| "x" |
| ], |
| [ |
| "Hel", |
| "lo" |
| ], |
| [ |
| "iz", |
| "er" |
| ], |
| [ |
| "mp", |
| "s" |
| ], |
| [ |
| "ow", |
| "n" |
| ], |
| [ |
| "Ġbr", |
| "own" |
| ], |
| [ |
| "Ġdo", |
| "g" |
| ], |
| [ |
| "Ġju", |
| "mps" |
| ], |
| [ |
| "Ġlaz", |
| "y" |
| ], |
| [ |
| "Ġmo", |
| "del" |
| ], |
| [ |
| "Ġqu", |
| "ick" |
| ], |
| [ |
| "Ġwor", |
| "ld" |
| ], |
| [ |
| "Ġtes", |
| "t" |
| ], |
| [ |
| "Ġtoken", |
| "izer" |
| ] |
| ] |
| } |
| } |