File size: 1,912 Bytes
f3eb8cb |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 |
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 9,
"content": ";",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": null,
"pre_tokenizer": {
"type": "Split",
"pattern": {
"Regex": "."
},
"behavior": "Isolated",
"invert": false
},
"post_processor": {
"type": "TemplateProcessing",
"single": [
{
"SpecialToken": {
"id": ";",
"type_id": 0
}
},
{
"Sequence": {
"id": "A",
"type_id": 0
}
}
],
"pair": [
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"Sequence": {
"id": "B",
"type_id": 1
}
}
],
"special_tokens": {
"": {
"id": "",
"ids": [
0
],
"tokens": [
""
]
},
";": {
"id": ";",
"ids": [
9
],
"tokens": [
";"
]
}
}
},
"decoder": {
"type": "Sequence",
"decoders": [
{
"type": "Replace",
"pattern": {
"String": " "
},
"content": "▁"
},
{
"type": "Replace",
"pattern": {
"String": "▁"
},
"content": " "
}
]
},
"model": {
"type": "WordLevel",
"vocab": {
" ": 0,
"1": 1,
"2": 2,
"3": 3,
"4": 4,
"5": 5,
"6": 6,
"7": 7,
"8": 8,
";": 9,
"#": 10,
"a": 11,
"b": 12,
"c": 13,
"d": 14,
"e": 15,
"f": 16,
"g": 17,
"h": 18,
"n": 19,
"r": 20,
"q": 21,
"k": 22
},
"unk_token": " "
}
} |