calculator_model_test / tokenizer.json
cvzx's picture
End of training
f6ef304 verified
raw
history blame
3.09 kB
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"content": "[EOS]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 1,
"content": "[UNK]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 2,
"content": "[CLS]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 3,
"content": "[PAD]",
"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
}
},
{
"SpecialToken": {
"id": "[EOS]",
"type_id": 0
}
}
],
"pair": [
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"Sequence": {
"id": "B",
"type_id": 1
}
}
],
"special_tokens": {
"[EOS]": {
"id": "[EOS]",
"ids": [
0
],
"tokens": [
"[EOS]"
]
}
}
},
"decoder": null,
"model": {
"type": "BPE",
"dropout": null,
"unk_token": "[UNK]",
"continuing_subword_prefix": null,
"end_of_word_suffix": null,
"fuse_unk": false,
"byte_fallback": false,
"vocab": {
"[EOS]": 0,
"[UNK]": 1,
"[CLS]": 2,
"[PAD]": 3,
"+": 4,
"-": 5,
"0": 6,
"1": 7,
"2": 8,
"3": 9,
"4": 10,
"5": 11,
"6": 12,
"7": 13,
"8": 14,
"9": 15,
"=": 16,
"10": 17,
"11": 18,
"12": 19,
"13": 20,
"14": 21,
"15": 22,
"99": 23,
"98": 24,
"16": 25,
"97": 26,
"96": 27,
"17": 28,
"95": 29,
"94": 30,
"18": 31,
"93": 32,
"92": 33,
"91": 34,
"19": 35,
"90": 36,
"20": 37,
"89": 38,
"21": 39,
"88": 40,
"22": 41,
"87": 42,
"86": 43,
"23": 44,
"24": 45,
"85": 46,
"84": 47,
"25": 48,
"83": 49,
"26": 50,
"27": 51,
"82": 52
},
"merges": [
"1 0",
"1 1",
"1 2",
"1 3",
"1 4",
"1 5",
"9 9",
"9 8",
"1 6",
"9 7",
"9 6",
"1 7",
"9 5",
"9 4",
"1 8",
"9 3",
"9 2",
"9 1",
"1 9",
"9 0",
"2 0",
"8 9",
"2 1",
"8 8",
"2 2",
"8 7",
"8 6",
"2 3",
"2 4",
"8 5",
"8 4",
"2 5",
"8 3",
"2 6",
"2 7",
"8 2"
]
}
}