calculator_model_test / tokenizer.json
ludziej's picture
End of training
014b724 verified
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 48,
"content": "[PAD]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 49,
"content": "[CLS]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 50,
"content": "[EOS]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": null,
"pre_tokenizer": {
"type": "Whitespace"
},
"post_processor": null,
"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,
"vocab": {
"+": 0,
"-": 1,
"0": 2,
"1": 3,
"2": 4,
"3": 5,
"4": 6,
"5": 7,
"6": 8,
"7": 9,
"8": 10,
"9": 11,
"=": 12,
"10": 13,
"99": 14,
"11": 15,
"98": 16,
"12": 17,
"97": 18,
"96": 19,
"13": 20,
"14": 21,
"95": 22,
"15": 23,
"94": 24,
"16": 25,
"93": 26,
"17": 27,
"92": 28,
"18": 29,
"91": 30,
"19": 31,
"90": 32,
"20": 33,
"89": 34,
"88": 35,
"21": 36,
"22": 37,
"87": 38,
"23": 39,
"86": 40,
"24": 41,
"85": 42,
"84": 43,
"25": 44,
"26": 45,
"83": 46,
"27": 47
},
"merges": [
"1 0",
"9 9",
"1 1",
"9 8",
"1 2",
"9 7",
"9 6",
"1 3",
"1 4",
"9 5",
"1 5",
"9 4",
"1 6",
"9 3",
"1 7",
"9 2",
"1 8",
"9 1",
"1 9",
"9 0",
"2 0",
"8 9",
"8 8",
"2 1",
"2 2",
"8 7",
"2 3",
"8 6",
"2 4",
"8 5",
"8 4",
"2 5",
"2 6",
"8 3",
"2 7"
]
}
}