| { | |
| "version": "1.0", | |
| "truncation": { | |
| "direction": "Right", | |
| "max_length": 512, | |
| "strategy": "LongestFirst", | |
| "stride": 0 | |
| }, | |
| "padding": { | |
| "strategy": { | |
| "Fixed": 512 | |
| }, | |
| "direction": "Left", | |
| "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": "</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 | |
| }, | |
| { | |
| "id": 4, | |
| "content": "<mask>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 5, | |
| "content": "Question:", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": false | |
| }, | |
| { | |
| "id": 6, | |
| "content": "RΓ©ponse:", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": false | |
| } | |
| ], | |
| "normalizer": { | |
| "type": "Replace", | |
| "pattern": { | |
| "String": " " | |
| }, | |
| "content": "β" | |
| }, | |
| "pre_tokenizer": null, | |
| "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": { | |
| "type": "Sequence", | |
| "decoders": [ | |
| { | |
| "type": "Replace", | |
| "pattern": { | |
| "String": "β" | |
| }, | |
| "content": " " | |
| }, | |
| { | |
| "type": "ByteFallback" | |
| }, | |
| { | |
| "type": "Fuse" | |
| } | |
| ] | |
| }, | |
| "model": { | |
| "type": "BPE", | |
| "dropout": null, | |
| "unk_token": "<unk>", | |
| "continuing_subword_prefix": null, | |
| "end_of_word_suffix": null, | |
| "fuse_unk": true, | |
| "byte_fallback": true, | |
| "ignore_merges": false, | |
| "vocab": { | |
| "<pad>": 0, | |
| "</s>": 1, | |
| "<s>": 2, | |
| "<unk>": 3, | |
| "<mask>": 4, | |
| "Question:": 5, | |
| "RΓ©ponse:": 6, | |
| "ββ": 7, | |
| "β-": 8, | |
| "βs": 9, | |
| "ol": 10, | |
| "βsol": 11, | |
| "do": 12, | |
| "βdo": 13, | |
| "mi": 14, | |
| "βmi": 15, | |
| "fa": 16, | |
| "βfa": 17, | |
| "la": 18, | |
| "βla": 19, | |
| "rΓ©": 20, | |
| "βrΓ©": 21, | |
| "βS": 22, | |
| "βsi": 23, | |
| "βSol": 24, | |
| "Do": 25, | |
| "βDo": 26, | |
| "La": 27, | |
| "βLa": 28, | |
| "Fa": 29, | |
| "Mi": 30, | |
| "RΓ©": 31, | |
| "βFa": 32, | |
| "βMi": 33, | |
| "βRΓ©": 34, | |
| "βSi": 35, | |
| "Si": 36, | |
| "So": 37, | |
| "si": 38, | |
| "so": 39, | |
| "βD": 40, | |
| "βF": 41, | |
| "βL": 42, | |
| "βM": 43, | |
| "βR": 44, | |
| "βd": 45, | |
| "βf": 46, | |
| "βl": 47, | |
| "βm": 48, | |
| "βr": 49, | |
| "Sol": 50, | |
| "βso": 51, | |
| "β": 52, | |
| "β": 53, | |
| "o": 54, | |
| "l": 55, | |
| "-": 56, | |
| "s": 57, | |
| "d": 58, | |
| "a": 59, | |
| "i": 60, | |
| "m": 61, | |
| "f": 62, | |
| "Γ©": 63, | |
| "r": 64, | |
| "#": 65, | |
| "S": 66, | |
| "D": 67, | |
| "L": 68, | |
| "F": 69, | |
| "M": 70, | |
| "R": 71 | |
| }, | |
| "merges": [ | |
| [ | |
| "β", | |
| "β" | |
| ], | |
| [ | |
| "β", | |
| "-" | |
| ], | |
| [ | |
| "β", | |
| "s" | |
| ], | |
| [ | |
| "o", | |
| "l" | |
| ], | |
| [ | |
| "βs", | |
| "ol" | |
| ], | |
| [ | |
| "βso", | |
| "l" | |
| ], | |
| [ | |
| "d", | |
| "o" | |
| ], | |
| [ | |
| "β", | |
| "do" | |
| ], | |
| [ | |
| "βd", | |
| "o" | |
| ], | |
| [ | |
| "m", | |
| "i" | |
| ], | |
| [ | |
| "β", | |
| "mi" | |
| ], | |
| [ | |
| "βm", | |
| "i" | |
| ], | |
| [ | |
| "f", | |
| "a" | |
| ], | |
| [ | |
| "β", | |
| "fa" | |
| ], | |
| [ | |
| "βf", | |
| "a" | |
| ], | |
| [ | |
| "l", | |
| "a" | |
| ], | |
| [ | |
| "β", | |
| "la" | |
| ], | |
| [ | |
| "βl", | |
| "a" | |
| ], | |
| [ | |
| "r", | |
| "Γ©" | |
| ], | |
| [ | |
| "β", | |
| "rΓ©" | |
| ], | |
| [ | |
| "βr", | |
| "Γ©" | |
| ], | |
| [ | |
| "β", | |
| "S" | |
| ], | |
| [ | |
| "β", | |
| "si" | |
| ], | |
| [ | |
| "βs", | |
| "i" | |
| ], | |
| [ | |
| "β", | |
| "Sol" | |
| ], | |
| [ | |
| "βS", | |
| "ol" | |
| ], | |
| [ | |
| "D", | |
| "o" | |
| ], | |
| [ | |
| "β", | |
| "Do" | |
| ], | |
| [ | |
| "βD", | |
| "o" | |
| ], | |
| [ | |
| "L", | |
| "a" | |
| ], | |
| [ | |
| "β", | |
| "La" | |
| ], | |
| [ | |
| "βL", | |
| "a" | |
| ], | |
| [ | |
| "F", | |
| "a" | |
| ], | |
| [ | |
| "M", | |
| "i" | |
| ], | |
| [ | |
| "R", | |
| "Γ©" | |
| ], | |
| [ | |
| "β", | |
| "Fa" | |
| ], | |
| [ | |
| "βF", | |
| "a" | |
| ], | |
| [ | |
| "β", | |
| "Mi" | |
| ], | |
| [ | |
| "βM", | |
| "i" | |
| ], | |
| [ | |
| "β", | |
| "RΓ©" | |
| ], | |
| [ | |
| "βR", | |
| "Γ©" | |
| ], | |
| [ | |
| "β", | |
| "Si" | |
| ], | |
| [ | |
| "βS", | |
| "i" | |
| ], | |
| [ | |
| "S", | |
| "i" | |
| ], | |
| [ | |
| "S", | |
| "o" | |
| ], | |
| [ | |
| "s", | |
| "i" | |
| ], | |
| [ | |
| "s", | |
| "o" | |
| ], | |
| [ | |
| "β", | |
| "D" | |
| ], | |
| [ | |
| "β", | |
| "F" | |
| ], | |
| [ | |
| "β", | |
| "L" | |
| ], | |
| [ | |
| "β", | |
| "M" | |
| ], | |
| [ | |
| "β", | |
| "R" | |
| ], | |
| [ | |
| "β", | |
| "d" | |
| ], | |
| [ | |
| "β", | |
| "f" | |
| ], | |
| [ | |
| "β", | |
| "l" | |
| ], | |
| [ | |
| "β", | |
| "m" | |
| ], | |
| [ | |
| "β", | |
| "r" | |
| ], | |
| [ | |
| "S", | |
| "ol" | |
| ], | |
| [ | |
| "So", | |
| "l" | |
| ], | |
| [ | |
| "β", | |
| "so" | |
| ], | |
| [ | |
| "βs", | |
| "o" | |
| ] | |
| ] | |
| } | |
| } |