Upload tokenizer
Browse files- special_tokens_map.json +9 -0
- tokenizer.json +753 -0
- tokenizer_config.json +16 -0
- vocab.txt +600 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": "[UNK]"
|
| 9 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,753 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
{
|
| 7 |
+
"id": 0,
|
| 8 |
+
"content": "[PAD]",
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"special": true
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"id": 1,
|
| 17 |
+
"content": "[CLS]",
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"special": true
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"id": 2,
|
| 26 |
+
"content": "[SEP]",
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"special": true
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"id": 3,
|
| 35 |
+
"content": "[UNK]",
|
| 36 |
+
"single_word": false,
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"special": true
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"id": 4,
|
| 44 |
+
"content": "[MASK]",
|
| 45 |
+
"single_word": false,
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"special": true
|
| 50 |
+
}
|
| 51 |
+
],
|
| 52 |
+
"normalizer": {
|
| 53 |
+
"type": "Sequence",
|
| 54 |
+
"normalizers": [
|
| 55 |
+
{
|
| 56 |
+
"type": "NFD"
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"type": "Lowercase"
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"type": "StripAccents"
|
| 63 |
+
}
|
| 64 |
+
]
|
| 65 |
+
},
|
| 66 |
+
"pre_tokenizer": {
|
| 67 |
+
"type": "Whitespace"
|
| 68 |
+
},
|
| 69 |
+
"post_processor": {
|
| 70 |
+
"type": "TemplateProcessing",
|
| 71 |
+
"single": [
|
| 72 |
+
{
|
| 73 |
+
"SpecialToken": {
|
| 74 |
+
"id": "[CLS]",
|
| 75 |
+
"type_id": 0
|
| 76 |
+
}
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"Sequence": {
|
| 80 |
+
"id": "A",
|
| 81 |
+
"type_id": 0
|
| 82 |
+
}
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"SpecialToken": {
|
| 86 |
+
"id": "[SEP]",
|
| 87 |
+
"type_id": 0
|
| 88 |
+
}
|
| 89 |
+
}
|
| 90 |
+
],
|
| 91 |
+
"pair": [
|
| 92 |
+
{
|
| 93 |
+
"SpecialToken": {
|
| 94 |
+
"id": "[CLS]",
|
| 95 |
+
"type_id": 0
|
| 96 |
+
}
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"Sequence": {
|
| 100 |
+
"id": "A",
|
| 101 |
+
"type_id": 0
|
| 102 |
+
}
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"SpecialToken": {
|
| 106 |
+
"id": "[SEP]",
|
| 107 |
+
"type_id": 0
|
| 108 |
+
}
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"Sequence": {
|
| 112 |
+
"id": "B",
|
| 113 |
+
"type_id": 1
|
| 114 |
+
}
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"SpecialToken": {
|
| 118 |
+
"id": "[SEP]",
|
| 119 |
+
"type_id": 1
|
| 120 |
+
}
|
| 121 |
+
}
|
| 122 |
+
],
|
| 123 |
+
"special_tokens": {
|
| 124 |
+
"[CLS]": {
|
| 125 |
+
"id": "[CLS]",
|
| 126 |
+
"ids": [
|
| 127 |
+
1
|
| 128 |
+
],
|
| 129 |
+
"tokens": [
|
| 130 |
+
"[CLS]"
|
| 131 |
+
]
|
| 132 |
+
},
|
| 133 |
+
"[SEP]": {
|
| 134 |
+
"id": "[SEP]",
|
| 135 |
+
"ids": [
|
| 136 |
+
2
|
| 137 |
+
],
|
| 138 |
+
"tokens": [
|
| 139 |
+
"[SEP]"
|
| 140 |
+
]
|
| 141 |
+
}
|
| 142 |
+
}
|
| 143 |
+
},
|
| 144 |
+
"decoder": null,
|
| 145 |
+
"model": {
|
| 146 |
+
"type": "WordPiece",
|
| 147 |
+
"unk_token": "[UNK]",
|
| 148 |
+
"continuing_subword_prefix": "##",
|
| 149 |
+
"max_input_chars_per_word": 100,
|
| 150 |
+
"vocab": {
|
| 151 |
+
"[PAD]": 0,
|
| 152 |
+
"[CLS]": 1,
|
| 153 |
+
"[SEP]": 2,
|
| 154 |
+
"[UNK]": 3,
|
| 155 |
+
"[MASK]": 4,
|
| 156 |
+
"\"": 5,
|
| 157 |
+
"%": 6,
|
| 158 |
+
"&": 7,
|
| 159 |
+
"'": 8,
|
| 160 |
+
"(": 9,
|
| 161 |
+
")": 10,
|
| 162 |
+
"*": 11,
|
| 163 |
+
"+": 12,
|
| 164 |
+
",": 13,
|
| 165 |
+
"-": 14,
|
| 166 |
+
".": 15,
|
| 167 |
+
"/": 16,
|
| 168 |
+
"0": 17,
|
| 169 |
+
"1": 18,
|
| 170 |
+
"2": 19,
|
| 171 |
+
"3": 20,
|
| 172 |
+
"4": 21,
|
| 173 |
+
"5": 22,
|
| 174 |
+
"6": 23,
|
| 175 |
+
"7": 24,
|
| 176 |
+
"8": 25,
|
| 177 |
+
"9": 26,
|
| 178 |
+
":": 27,
|
| 179 |
+
";": 28,
|
| 180 |
+
"<": 29,
|
| 181 |
+
"=": 30,
|
| 182 |
+
">": 31,
|
| 183 |
+
"[": 32,
|
| 184 |
+
"]": 33,
|
| 185 |
+
"_": 34,
|
| 186 |
+
"a": 35,
|
| 187 |
+
"b": 36,
|
| 188 |
+
"c": 37,
|
| 189 |
+
"d": 38,
|
| 190 |
+
"e": 39,
|
| 191 |
+
"f": 40,
|
| 192 |
+
"g": 41,
|
| 193 |
+
"h": 42,
|
| 194 |
+
"i": 43,
|
| 195 |
+
"j": 44,
|
| 196 |
+
"k": 45,
|
| 197 |
+
"l": 46,
|
| 198 |
+
"m": 47,
|
| 199 |
+
"n": 48,
|
| 200 |
+
"o": 49,
|
| 201 |
+
"p": 50,
|
| 202 |
+
"q": 51,
|
| 203 |
+
"r": 52,
|
| 204 |
+
"s": 53,
|
| 205 |
+
"t": 54,
|
| 206 |
+
"u": 55,
|
| 207 |
+
"v": 56,
|
| 208 |
+
"w": 57,
|
| 209 |
+
"x": 58,
|
| 210 |
+
"y": 59,
|
| 211 |
+
"z": 60,
|
| 212 |
+
"~": 61,
|
| 213 |
+
"®": 62,
|
| 214 |
+
"°": 63,
|
| 215 |
+
"²": 64,
|
| 216 |
+
"³": 65,
|
| 217 |
+
"µ": 66,
|
| 218 |
+
"ø": 67,
|
| 219 |
+
"α": 68,
|
| 220 |
+
"–": 69,
|
| 221 |
+
"##r": 70,
|
| 222 |
+
"##i": 71,
|
| 223 |
+
"##c": 72,
|
| 224 |
+
"##h": 73,
|
| 225 |
+
"##l": 74,
|
| 226 |
+
"##o": 75,
|
| 227 |
+
"##d": 76,
|
| 228 |
+
"##e": 77,
|
| 229 |
+
"##n": 78,
|
| 230 |
+
"##s": 79,
|
| 231 |
+
"##a": 80,
|
| 232 |
+
"##m": 81,
|
| 233 |
+
"##t": 82,
|
| 234 |
+
"##5": 83,
|
| 235 |
+
"##x": 84,
|
| 236 |
+
"##3": 85,
|
| 237 |
+
"##2": 86,
|
| 238 |
+
"##,": 87,
|
| 239 |
+
"##p": 88,
|
| 240 |
+
"##b": 89,
|
| 241 |
+
"##4": 90,
|
| 242 |
+
"##1": 91,
|
| 243 |
+
"##u": 92,
|
| 244 |
+
"##8": 93,
|
| 245 |
+
"##6": 94,
|
| 246 |
+
"##y": 95,
|
| 247 |
+
"##7": 96,
|
| 248 |
+
"##k": 97,
|
| 249 |
+
"##g": 98,
|
| 250 |
+
"##0": 99,
|
| 251 |
+
"##w": 100,
|
| 252 |
+
"##9": 101,
|
| 253 |
+
"##q": 102,
|
| 254 |
+
"##f": 103,
|
| 255 |
+
"##z": 104,
|
| 256 |
+
"##v": 105,
|
| 257 |
+
"##µ": 106,
|
| 258 |
+
"##)": 107,
|
| 259 |
+
"##\"": 108,
|
| 260 |
+
"##j": 109,
|
| 261 |
+
"##<": 110,
|
| 262 |
+
"##=": 111,
|
| 263 |
+
"##(": 112,
|
| 264 |
+
"##%": 113,
|
| 265 |
+
"##_": 114,
|
| 266 |
+
"##-": 115,
|
| 267 |
+
"##;": 116,
|
| 268 |
+
"##]": 117,
|
| 269 |
+
"##>": 118,
|
| 270 |
+
"##/": 119,
|
| 271 |
+
"##ø": 120,
|
| 272 |
+
"##er": 121,
|
| 273 |
+
"##in": 122,
|
| 274 |
+
"##on": 123,
|
| 275 |
+
"##at": 124,
|
| 276 |
+
"##ed": 125,
|
| 277 |
+
"##ro": 126,
|
| 278 |
+
"##en": 127,
|
| 279 |
+
"##an": 128,
|
| 280 |
+
"##ic": 129,
|
| 281 |
+
"##as": 130,
|
| 282 |
+
"##ar": 131,
|
| 283 |
+
"##or": 132,
|
| 284 |
+
"##al": 133,
|
| 285 |
+
"##ct": 134,
|
| 286 |
+
"##it": 135,
|
| 287 |
+
"##ol": 136,
|
| 288 |
+
"##il": 137,
|
| 289 |
+
"##ion": 138,
|
| 290 |
+
"##ing": 139,
|
| 291 |
+
"##es": 140,
|
| 292 |
+
"##et": 141,
|
| 293 |
+
"##el": 142,
|
| 294 |
+
"##id": 143,
|
| 295 |
+
"in": 144,
|
| 296 |
+
"##le": 145,
|
| 297 |
+
"tr": 146,
|
| 298 |
+
"##um": 147,
|
| 299 |
+
"##yl": 148,
|
| 300 |
+
"en": 149,
|
| 301 |
+
"##ent": 150,
|
| 302 |
+
"##te": 151,
|
| 303 |
+
"##re": 152,
|
| 304 |
+
"##ation": 153,
|
| 305 |
+
"co": 154,
|
| 306 |
+
"##st": 155,
|
| 307 |
+
"##od": 156,
|
| 308 |
+
"pl": 157,
|
| 309 |
+
"##am": 158,
|
| 310 |
+
"##rom": 159,
|
| 311 |
+
"con": 160,
|
| 312 |
+
"##ity": 161,
|
| 313 |
+
"##80": 162,
|
| 314 |
+
"##ric": 163,
|
| 315 |
+
"##ul": 164,
|
| 316 |
+
"di": 165,
|
| 317 |
+
"from": 166,
|
| 318 |
+
"##ene": 167,
|
| 319 |
+
"##ig": 168,
|
| 320 |
+
"##580": 169,
|
| 321 |
+
"##5804": 170,
|
| 322 |
+
"pro": 171,
|
| 323 |
+
"ele": 172,
|
| 324 |
+
"##ut": 173,
|
| 325 |
+
"##ck": 174,
|
| 326 |
+
"re": 175,
|
| 327 |
+
"elect": 176,
|
| 328 |
+
"##lo": 177,
|
| 329 |
+
"##ur": 178,
|
| 330 |
+
"##ate": 179,
|
| 331 |
+
"a3": 180,
|
| 332 |
+
"a1": 181,
|
| 333 |
+
"##ad": 182,
|
| 334 |
+
"al": 183,
|
| 335 |
+
"##ix": 184,
|
| 336 |
+
"##ated": 185,
|
| 337 |
+
"pa": 186,
|
| 338 |
+
"##igh": 187,
|
| 339 |
+
"##ine": 188,
|
| 340 |
+
"##du": 189,
|
| 341 |
+
"##oly": 190,
|
| 342 |
+
"mix": 191,
|
| 343 |
+
"##ac": 192,
|
| 344 |
+
"car": 193,
|
| 345 |
+
"ste": 194,
|
| 346 |
+
"at": 195,
|
| 347 |
+
"##ood": 196,
|
| 348 |
+
"st": 197,
|
| 349 |
+
"electric": 198,
|
| 350 |
+
"##ow": 199,
|
| 351 |
+
"##im": 200,
|
| 352 |
+
"##sp": 201,
|
| 353 |
+
"##em": 202,
|
| 354 |
+
"##ium": 203,
|
| 355 |
+
"20": 204,
|
| 356 |
+
"gr": 205,
|
| 357 |
+
"poly": 206,
|
| 358 |
+
"##ard": 207,
|
| 359 |
+
"##eth": 208,
|
| 360 |
+
"##ap": 209,
|
| 361 |
+
"##ill": 210,
|
| 362 |
+
"mm": 211,
|
| 363 |
+
"electricity": 212,
|
| 364 |
+
"##uck": 213,
|
| 365 |
+
"truck": 214,
|
| 366 |
+
"##ip": 215,
|
| 367 |
+
"##ber": 216,
|
| 368 |
+
"##ch": 217,
|
| 369 |
+
"##duct": 218,
|
| 370 |
+
"##15804": 219,
|
| 371 |
+
"en15804": 220,
|
| 372 |
+
"cont": 221,
|
| 373 |
+
"##pp": 222,
|
| 374 |
+
"##ort": 223,
|
| 375 |
+
"##ide": 224,
|
| 376 |
+
"##ight": 225,
|
| 377 |
+
"plan": 226,
|
| 378 |
+
"sh": 227,
|
| 379 |
+
"of": 228,
|
| 380 |
+
"##nd": 229,
|
| 381 |
+
"##ast": 230,
|
| 382 |
+
"product": 231,
|
| 383 |
+
"##oad": 232,
|
| 384 |
+
"##eat": 233,
|
| 385 |
+
"##ge": 234,
|
| 386 |
+
"##wood": 235,
|
| 387 |
+
"##ased": 236,
|
| 388 |
+
"pow": 237,
|
| 389 |
+
"steel": 238,
|
| 390 |
+
"##ver": 239,
|
| 391 |
+
"##ess": 240,
|
| 392 |
+
"ac": 241,
|
| 393 |
+
"##ater": 242,
|
| 394 |
+
"##00": 243,
|
| 395 |
+
"##and": 244,
|
| 396 |
+
"content": 245,
|
| 397 |
+
"par": 246,
|
| 398 |
+
"##ri": 247,
|
| 399 |
+
"com": 248,
|
| 400 |
+
"ro": 249,
|
| 401 |
+
"was": 250,
|
| 402 |
+
"##yload": 251,
|
| 403 |
+
"payload": 252,
|
| 404 |
+
"##th": 253,
|
| 405 |
+
"ch": 254,
|
| 406 |
+
"##ist": 255,
|
| 407 |
+
"##ter": 256,
|
| 408 |
+
"##of": 257,
|
| 409 |
+
"fi": 258,
|
| 410 |
+
"gas": 259,
|
| 411 |
+
"##ass": 260,
|
| 412 |
+
"waste": 261,
|
| 413 |
+
"cap": 262,
|
| 414 |
+
"##ylene": 263,
|
| 415 |
+
"gro": 264,
|
| 416 |
+
"##ith": 265,
|
| 417 |
+
"##ane": 266,
|
| 418 |
+
"power": 267,
|
| 419 |
+
"tran": 268,
|
| 420 |
+
"##cl": 269,
|
| 421 |
+
"15804": 270,
|
| 422 |
+
"app": 271,
|
| 423 |
+
"based": 272,
|
| 424 |
+
"##is": 273,
|
| 425 |
+
"capac": 274,
|
| 426 |
+
"##ure": 275,
|
| 427 |
+
"th": 276,
|
| 428 |
+
"and": 277,
|
| 429 |
+
"water": 278,
|
| 430 |
+
"##om": 279,
|
| 431 |
+
"plant": 280,
|
| 432 |
+
"for": 281,
|
| 433 |
+
"un": 282,
|
| 434 |
+
"##led": 283,
|
| 435 |
+
"grid": 284,
|
| 436 |
+
"##eet": 285,
|
| 437 |
+
"##us": 286,
|
| 438 |
+
"part": 287,
|
| 439 |
+
"##2o": 288,
|
| 440 |
+
"##yd": 289,
|
| 441 |
+
"##est": 290,
|
| 442 |
+
"##old": 291,
|
| 443 |
+
"by": 292,
|
| 444 |
+
"##co": 293,
|
| 445 |
+
"oil": 294,
|
| 446 |
+
"##ce": 295,
|
| 447 |
+
"##eight": 296,
|
| 448 |
+
"bo": 297,
|
| 449 |
+
"##rox": 298,
|
| 450 |
+
"res": 299,
|
| 451 |
+
"##gy": 300,
|
| 452 |
+
"##ss": 301,
|
| 453 |
+
"##aw": 302,
|
| 454 |
+
"sheet": 303,
|
| 455 |
+
"h2o": 304,
|
| 456 |
+
"us": 305,
|
| 457 |
+
"##ly": 306,
|
| 458 |
+
"with": 307,
|
| 459 |
+
"##esel": 308,
|
| 460 |
+
"transp": 309,
|
| 461 |
+
"capacity": 310,
|
| 462 |
+
"mo": 311,
|
| 463 |
+
"##iner": 312,
|
| 464 |
+
"transport": 313,
|
| 465 |
+
"##uro": 314,
|
| 466 |
+
"weight": 315,
|
| 467 |
+
"##iz": 316,
|
| 468 |
+
"),": 317,
|
| 469 |
+
"##bon": 318,
|
| 470 |
+
"bi": 319,
|
| 471 |
+
"on": 320,
|
| 472 |
+
"##ergy": 321,
|
| 473 |
+
"diesel": 322,
|
| 474 |
+
"energy": 323,
|
| 475 |
+
"euro": 324,
|
| 476 |
+
"##un": 325,
|
| 477 |
+
"##lu": 326,
|
| 478 |
+
"##rect": 327,
|
| 479 |
+
"##age": 328,
|
| 480 |
+
"approx": 329,
|
| 481 |
+
"se": 330,
|
| 482 |
+
"gross": 331,
|
| 483 |
+
"carbon": 332,
|
| 484 |
+
"cr": 333,
|
| 485 |
+
"##imation": 334,
|
| 486 |
+
"approximation": 335,
|
| 487 |
+
"##cy": 336,
|
| 488 |
+
"##ment": 337,
|
| 489 |
+
"##fill": 338,
|
| 490 |
+
"to": 339,
|
| 491 |
+
"12": 340,
|
| 492 |
+
"acid": 341,
|
| 493 |
+
"land": 342,
|
| 494 |
+
"##umin": 343,
|
| 495 |
+
"op": 344,
|
| 496 |
+
"##ug": 345,
|
| 497 |
+
"##av": 346,
|
| 498 |
+
"landfill": 347,
|
| 499 |
+
"##ial": 348,
|
| 500 |
+
"alumin": 349,
|
| 501 |
+
"##mm": 350,
|
| 502 |
+
"##put": 351,
|
| 503 |
+
"##ural": 352,
|
| 504 |
+
"allo": 353,
|
| 505 |
+
"##cess": 354,
|
| 506 |
+
"fiber": 355,
|
| 507 |
+
"eth": 356,
|
| 508 |
+
"powered": 357,
|
| 509 |
+
"process": 358,
|
| 510 |
+
"production": 359,
|
| 511 |
+
"ex": 360,
|
| 512 |
+
"vd": 361,
|
| 513 |
+
"##act": 362,
|
| 514 |
+
"moist": 363,
|
| 515 |
+
"alloc": 364,
|
| 516 |
+
"##iv": 365,
|
| 517 |
+
"##cr": 366,
|
| 518 |
+
"##ain": 367,
|
| 519 |
+
"##lor": 368,
|
| 520 |
+
"##ab": 369,
|
| 521 |
+
"de": 370,
|
| 522 |
+
"##mg": 371,
|
| 523 |
+
"hyd": 372,
|
| 524 |
+
"kw": 373,
|
| 525 |
+
"pr": 374,
|
| 526 |
+
"##ile": 375,
|
| 527 |
+
"##one": 376,
|
| 528 |
+
"moisture": 377,
|
| 529 |
+
"hard": 378,
|
| 530 |
+
"##amine": 379,
|
| 531 |
+
"rol": 380,
|
| 532 |
+
"open": 381,
|
| 533 |
+
"##os": 382,
|
| 534 |
+
"##all": 383,
|
| 535 |
+
"te": 384,
|
| 536 |
+
"##ne": 385,
|
| 537 |
+
"##iler": 386,
|
| 538 |
+
"##con": 387,
|
| 539 |
+
"##for": 388,
|
| 540 |
+
"kg": 389,
|
| 541 |
+
"##erm": 390,
|
| 542 |
+
"dri": 391,
|
| 543 |
+
"input": 392,
|
| 544 |
+
"comp": 393,
|
| 545 |
+
"cf": 394,
|
| 546 |
+
"so": 395,
|
| 547 |
+
"cem": 396,
|
| 548 |
+
"##ph": 397,
|
| 549 |
+
"treat": 398,
|
| 550 |
+
"treatment": 399,
|
| 551 |
+
"ag": 400,
|
| 552 |
+
"lc": 401,
|
| 553 |
+
"##der": 402,
|
| 554 |
+
"allocation": 403,
|
| 555 |
+
"rolled": 404,
|
| 556 |
+
"flo": 405,
|
| 557 |
+
"mun": 406,
|
| 558 |
+
"##icip": 407,
|
| 559 |
+
"##ctor": 408,
|
| 560 |
+
"plast": 409,
|
| 561 |
+
"roof": 410,
|
| 562 |
+
"municip": 411,
|
| 563 |
+
"municipal": 412,
|
| 564 |
+
"10": 413,
|
| 565 |
+
"cold": 414,
|
| 566 |
+
"##ay": 415,
|
| 567 |
+
"##pe": 416,
|
| 568 |
+
"##verage": 417,
|
| 569 |
+
"average": 418,
|
| 570 |
+
"##cycl": 419,
|
| 571 |
+
"recycl": 420,
|
| 572 |
+
"dried": 421,
|
| 573 |
+
"meth": 422,
|
| 574 |
+
"wood": 423,
|
| 575 |
+
"ep": 424,
|
| 576 |
+
"nat": 425,
|
| 577 |
+
"##br": 426,
|
| 578 |
+
"##og": 427,
|
| 579 |
+
"60": 428,
|
| 580 |
+
"##ance": 429,
|
| 581 |
+
"201": 430,
|
| 582 |
+
"natural": 431,
|
| 583 |
+
"steam": 432,
|
| 584 |
+
"aluminium": 433,
|
| 585 |
+
"##ite": 434,
|
| 586 |
+
"therm": 435,
|
| 587 |
+
"high": 436,
|
| 588 |
+
"wh": 437,
|
| 589 |
+
"##di": 438,
|
| 590 |
+
"##sion": 439,
|
| 591 |
+
"reg": 440,
|
| 592 |
+
"##ot": 441,
|
| 593 |
+
"14": 442,
|
| 594 |
+
"##bo": 443,
|
| 595 |
+
"##uel": 444,
|
| 596 |
+
"pan": 445,
|
| 597 |
+
"ply": 446,
|
| 598 |
+
"fuel": 447,
|
| 599 |
+
"hydro": 448,
|
| 600 |
+
"ha": 449,
|
| 601 |
+
"mod": 450,
|
| 602 |
+
"sol": 451,
|
| 603 |
+
"##ir": 452,
|
| 604 |
+
"##lass": 453,
|
| 605 |
+
"##ub": 454,
|
| 606 |
+
"##ust": 455,
|
| 607 |
+
"conne": 456,
|
| 608 |
+
"connector": 457,
|
| 609 |
+
"c3": 458,
|
| 610 |
+
"lum": 459,
|
| 611 |
+
"inc": 460,
|
| 612 |
+
"chlor": 461,
|
| 613 |
+
"region": 462,
|
| 614 |
+
"eg": 463,
|
| 615 |
+
"sof": 464,
|
| 616 |
+
"##ry": 465,
|
| 617 |
+
"##sul": 466,
|
| 618 |
+
"coated": 467,
|
| 619 |
+
"floor": 468,
|
| 620 |
+
"soft": 469,
|
| 621 |
+
"cor": 470,
|
| 622 |
+
"light": 471,
|
| 623 |
+
"comb": 472,
|
| 624 |
+
"board": 473,
|
| 625 |
+
"lumber": 474,
|
| 626 |
+
"c4": 475,
|
| 627 |
+
"##kv": 476,
|
| 628 |
+
"kil": 477,
|
| 629 |
+
"mel": 478,
|
| 630 |
+
"kiln": 479,
|
| 631 |
+
"bf": 480,
|
| 632 |
+
"coat": 481,
|
| 633 |
+
"a5": 482,
|
| 634 |
+
"recycling": 483,
|
| 635 |
+
"##x1": 484,
|
| 636 |
+
"##ical": 485,
|
| 637 |
+
"inciner": 486,
|
| 638 |
+
"##mer": 487,
|
| 639 |
+
"haul": 488,
|
| 640 |
+
"##ens": 489,
|
| 641 |
+
"##ode": 490,
|
| 642 |
+
"cut": 491,
|
| 643 |
+
"fl": 492,
|
| 644 |
+
"he": 493,
|
| 645 |
+
"pet": 494,
|
| 646 |
+
"up": 495,
|
| 647 |
+
"##anul": 496,
|
| 648 |
+
"direct": 497,
|
| 649 |
+
"granul": 498,
|
| 650 |
+
"incineration": 499,
|
| 651 |
+
"heat": 500,
|
| 652 |
+
"melamine": 501,
|
| 653 |
+
"but": 502,
|
| 654 |
+
"softwood": 503,
|
| 655 |
+
"rene": 504,
|
| 656 |
+
"insul": 505,
|
| 657 |
+
"200": 506,
|
| 658 |
+
"vda": 507,
|
| 659 |
+
"cement": 508,
|
| 660 |
+
"renew": 509,
|
| 661 |
+
"e1": 510,
|
| 662 |
+
"##ethane": 511,
|
| 663 |
+
"15": 512,
|
| 664 |
+
"pin": 513,
|
| 665 |
+
"##uf": 514,
|
| 666 |
+
"##dust": 515,
|
| 667 |
+
"25": 516,
|
| 668 |
+
"hd": 517,
|
| 669 |
+
"sm": 518,
|
| 670 |
+
"sy": 519,
|
| 671 |
+
"slu": 520,
|
| 672 |
+
"##ia": 521,
|
| 673 |
+
"##op": 522,
|
| 674 |
+
"##dge": 523,
|
| 675 |
+
"##yp": 524,
|
| 676 |
+
"##int": 525,
|
| 677 |
+
"##ingle": 526,
|
| 678 |
+
"dist": 527,
|
| 679 |
+
"roofing": 528,
|
| 680 |
+
"granulate": 529,
|
| 681 |
+
"sludge": 530,
|
| 682 |
+
"mill": 531,
|
| 683 |
+
"sp": 532,
|
| 684 |
+
"##ding": 533,
|
| 685 |
+
"electr": 534,
|
| 686 |
+
"##board": 535,
|
| 687 |
+
"##if": 536,
|
| 688 |
+
"##ue": 537,
|
| 689 |
+
"##ong": 538,
|
| 690 |
+
"flooring": 539,
|
| 691 |
+
"22": 540,
|
| 692 |
+
"fo": 541,
|
| 693 |
+
"pe": 542,
|
| 694 |
+
"##infor": 543,
|
| 695 |
+
"reinfor": 544,
|
| 696 |
+
"reinforc": 545,
|
| 697 |
+
"##ied": 546,
|
| 698 |
+
"##ox": 547,
|
| 699 |
+
"##tr": 548,
|
| 700 |
+
"mem": 549,
|
| 701 |
+
"##ive": 550,
|
| 702 |
+
"nm": 551,
|
| 703 |
+
"single": 552,
|
| 704 |
+
"##per": 553,
|
| 705 |
+
"##fin": 554,
|
| 706 |
+
"##icle": 555,
|
| 707 |
+
"incl": 556,
|
| 708 |
+
"##sph": 557,
|
| 709 |
+
"tex": 558,
|
| 710 |
+
"plywood": 559,
|
| 711 |
+
"model": 560,
|
| 712 |
+
"18": 561,
|
| 713 |
+
"16": 562,
|
| 714 |
+
"man": 563,
|
| 715 |
+
"ph": 564,
|
| 716 |
+
"saw": 565,
|
| 717 |
+
"##oline": 566,
|
| 718 |
+
"indi": 567,
|
| 719 |
+
"gasoline": 568,
|
| 720 |
+
"indirect": 569,
|
| 721 |
+
"dw": 570,
|
| 722 |
+
"##yr": 571,
|
| 723 |
+
"##ete": 572,
|
| 724 |
+
"##ell": 573,
|
| 725 |
+
"resist": 574,
|
| 726 |
+
"hardwood": 575,
|
| 727 |
+
"sil": 576,
|
| 728 |
+
"##anol": 577,
|
| 729 |
+
"ba": 578,
|
| 730 |
+
"coating": 579,
|
| 731 |
+
"000": 580,
|
| 732 |
+
"pip": 581,
|
| 733 |
+
"##ool": 582,
|
| 734 |
+
"boiler": 583,
|
| 735 |
+
"sul": 584,
|
| 736 |
+
"indust": 585,
|
| 737 |
+
"membr": 586,
|
| 738 |
+
"##ous": 587,
|
| 739 |
+
"##ides": 588,
|
| 740 |
+
"##crete": 589,
|
| 741 |
+
"membrane": 590,
|
| 742 |
+
"resin": 591,
|
| 743 |
+
"insulation": 592,
|
| 744 |
+
"32": 593,
|
| 745 |
+
"econ": 594,
|
| 746 |
+
"ic": 595,
|
| 747 |
+
"econom": 596,
|
| 748 |
+
"pv": 597,
|
| 749 |
+
"##ru": 598,
|
| 750 |
+
"##hyd": 599
|
| 751 |
+
}
|
| 752 |
+
}
|
| 753 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_lower_case": true,
|
| 5 |
+
"eos_token": "[SEP]",
|
| 6 |
+
"mask_token": "[MASK]",
|
| 7 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 8 |
+
"name_or_path": "/Users/avinashronanki/PycharmProjects/machine_learning/modules/tokenization_pipeline/new_tokenizer",
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"special_tokens_map_file": "/Users/avinashronanki/PycharmProjects/machine_learning/modules/tokenization_pipeline/new_tokenizer/special_tokens_map.json",
|
| 12 |
+
"strip_accents": null,
|
| 13 |
+
"tokenize_chinese_chars": true,
|
| 14 |
+
"tokenizer_class": "BertTokenizer",
|
| 15 |
+
"unk_token": "[UNK]"
|
| 16 |
+
}
|
vocab.txt
ADDED
|
@@ -0,0 +1,600 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[PAD]
|
| 2 |
+
[CLS]
|
| 3 |
+
[SEP]
|
| 4 |
+
[UNK]
|
| 5 |
+
[MASK]
|
| 6 |
+
"
|
| 7 |
+
%
|
| 8 |
+
&
|
| 9 |
+
'
|
| 10 |
+
(
|
| 11 |
+
)
|
| 12 |
+
*
|
| 13 |
+
+
|
| 14 |
+
,
|
| 15 |
+
-
|
| 16 |
+
.
|
| 17 |
+
/
|
| 18 |
+
0
|
| 19 |
+
1
|
| 20 |
+
2
|
| 21 |
+
3
|
| 22 |
+
4
|
| 23 |
+
5
|
| 24 |
+
6
|
| 25 |
+
7
|
| 26 |
+
8
|
| 27 |
+
9
|
| 28 |
+
:
|
| 29 |
+
;
|
| 30 |
+
<
|
| 31 |
+
=
|
| 32 |
+
>
|
| 33 |
+
[
|
| 34 |
+
]
|
| 35 |
+
_
|
| 36 |
+
a
|
| 37 |
+
b
|
| 38 |
+
c
|
| 39 |
+
d
|
| 40 |
+
e
|
| 41 |
+
f
|
| 42 |
+
g
|
| 43 |
+
h
|
| 44 |
+
i
|
| 45 |
+
j
|
| 46 |
+
k
|
| 47 |
+
l
|
| 48 |
+
m
|
| 49 |
+
n
|
| 50 |
+
o
|
| 51 |
+
p
|
| 52 |
+
q
|
| 53 |
+
r
|
| 54 |
+
s
|
| 55 |
+
t
|
| 56 |
+
u
|
| 57 |
+
v
|
| 58 |
+
w
|
| 59 |
+
x
|
| 60 |
+
y
|
| 61 |
+
z
|
| 62 |
+
~
|
| 63 |
+
®
|
| 64 |
+
°
|
| 65 |
+
²
|
| 66 |
+
³
|
| 67 |
+
µ
|
| 68 |
+
ø
|
| 69 |
+
α
|
| 70 |
+
–
|
| 71 |
+
##r
|
| 72 |
+
##i
|
| 73 |
+
##c
|
| 74 |
+
##h
|
| 75 |
+
##l
|
| 76 |
+
##o
|
| 77 |
+
##d
|
| 78 |
+
##e
|
| 79 |
+
##n
|
| 80 |
+
##s
|
| 81 |
+
##a
|
| 82 |
+
##m
|
| 83 |
+
##t
|
| 84 |
+
##5
|
| 85 |
+
##x
|
| 86 |
+
##3
|
| 87 |
+
##2
|
| 88 |
+
##,
|
| 89 |
+
##p
|
| 90 |
+
##b
|
| 91 |
+
##4
|
| 92 |
+
##1
|
| 93 |
+
##u
|
| 94 |
+
##8
|
| 95 |
+
##6
|
| 96 |
+
##y
|
| 97 |
+
##7
|
| 98 |
+
##k
|
| 99 |
+
##g
|
| 100 |
+
##0
|
| 101 |
+
##w
|
| 102 |
+
##9
|
| 103 |
+
##q
|
| 104 |
+
##f
|
| 105 |
+
##z
|
| 106 |
+
##v
|
| 107 |
+
##µ
|
| 108 |
+
##)
|
| 109 |
+
##"
|
| 110 |
+
##j
|
| 111 |
+
##<
|
| 112 |
+
##=
|
| 113 |
+
##(
|
| 114 |
+
##%
|
| 115 |
+
##_
|
| 116 |
+
##-
|
| 117 |
+
##;
|
| 118 |
+
##]
|
| 119 |
+
##>
|
| 120 |
+
##/
|
| 121 |
+
##ø
|
| 122 |
+
##er
|
| 123 |
+
##in
|
| 124 |
+
##on
|
| 125 |
+
##at
|
| 126 |
+
##ed
|
| 127 |
+
##ro
|
| 128 |
+
##en
|
| 129 |
+
##an
|
| 130 |
+
##ic
|
| 131 |
+
##as
|
| 132 |
+
##ar
|
| 133 |
+
##or
|
| 134 |
+
##al
|
| 135 |
+
##ct
|
| 136 |
+
##it
|
| 137 |
+
##ol
|
| 138 |
+
##il
|
| 139 |
+
##ion
|
| 140 |
+
##ing
|
| 141 |
+
##es
|
| 142 |
+
##et
|
| 143 |
+
##el
|
| 144 |
+
##id
|
| 145 |
+
in
|
| 146 |
+
##le
|
| 147 |
+
tr
|
| 148 |
+
##um
|
| 149 |
+
##yl
|
| 150 |
+
en
|
| 151 |
+
##ent
|
| 152 |
+
##te
|
| 153 |
+
##re
|
| 154 |
+
##ation
|
| 155 |
+
co
|
| 156 |
+
##st
|
| 157 |
+
##od
|
| 158 |
+
pl
|
| 159 |
+
##am
|
| 160 |
+
##rom
|
| 161 |
+
con
|
| 162 |
+
##ity
|
| 163 |
+
##80
|
| 164 |
+
##ric
|
| 165 |
+
##ul
|
| 166 |
+
di
|
| 167 |
+
from
|
| 168 |
+
##ene
|
| 169 |
+
##ig
|
| 170 |
+
##580
|
| 171 |
+
##5804
|
| 172 |
+
pro
|
| 173 |
+
ele
|
| 174 |
+
##ut
|
| 175 |
+
##ck
|
| 176 |
+
re
|
| 177 |
+
elect
|
| 178 |
+
##lo
|
| 179 |
+
##ur
|
| 180 |
+
##ate
|
| 181 |
+
a3
|
| 182 |
+
a1
|
| 183 |
+
##ad
|
| 184 |
+
al
|
| 185 |
+
##ix
|
| 186 |
+
##ated
|
| 187 |
+
pa
|
| 188 |
+
##igh
|
| 189 |
+
##ine
|
| 190 |
+
##du
|
| 191 |
+
##oly
|
| 192 |
+
mix
|
| 193 |
+
##ac
|
| 194 |
+
car
|
| 195 |
+
ste
|
| 196 |
+
at
|
| 197 |
+
##ood
|
| 198 |
+
st
|
| 199 |
+
electric
|
| 200 |
+
##ow
|
| 201 |
+
##im
|
| 202 |
+
##sp
|
| 203 |
+
##em
|
| 204 |
+
##ium
|
| 205 |
+
20
|
| 206 |
+
gr
|
| 207 |
+
poly
|
| 208 |
+
##ard
|
| 209 |
+
##eth
|
| 210 |
+
##ap
|
| 211 |
+
##ill
|
| 212 |
+
mm
|
| 213 |
+
electricity
|
| 214 |
+
##uck
|
| 215 |
+
truck
|
| 216 |
+
##ip
|
| 217 |
+
##ber
|
| 218 |
+
##ch
|
| 219 |
+
##duct
|
| 220 |
+
##15804
|
| 221 |
+
en15804
|
| 222 |
+
cont
|
| 223 |
+
##pp
|
| 224 |
+
##ort
|
| 225 |
+
##ide
|
| 226 |
+
##ight
|
| 227 |
+
plan
|
| 228 |
+
sh
|
| 229 |
+
of
|
| 230 |
+
##nd
|
| 231 |
+
##ast
|
| 232 |
+
product
|
| 233 |
+
##oad
|
| 234 |
+
##eat
|
| 235 |
+
##ge
|
| 236 |
+
##wood
|
| 237 |
+
##ased
|
| 238 |
+
pow
|
| 239 |
+
steel
|
| 240 |
+
##ver
|
| 241 |
+
##ess
|
| 242 |
+
ac
|
| 243 |
+
##ater
|
| 244 |
+
##00
|
| 245 |
+
##and
|
| 246 |
+
content
|
| 247 |
+
par
|
| 248 |
+
##ri
|
| 249 |
+
com
|
| 250 |
+
ro
|
| 251 |
+
was
|
| 252 |
+
##yload
|
| 253 |
+
payload
|
| 254 |
+
##th
|
| 255 |
+
ch
|
| 256 |
+
##ist
|
| 257 |
+
##ter
|
| 258 |
+
##of
|
| 259 |
+
fi
|
| 260 |
+
gas
|
| 261 |
+
##ass
|
| 262 |
+
waste
|
| 263 |
+
cap
|
| 264 |
+
##ylene
|
| 265 |
+
gro
|
| 266 |
+
##ith
|
| 267 |
+
##ane
|
| 268 |
+
power
|
| 269 |
+
tran
|
| 270 |
+
##cl
|
| 271 |
+
15804
|
| 272 |
+
app
|
| 273 |
+
based
|
| 274 |
+
##is
|
| 275 |
+
capac
|
| 276 |
+
##ure
|
| 277 |
+
th
|
| 278 |
+
and
|
| 279 |
+
water
|
| 280 |
+
##om
|
| 281 |
+
plant
|
| 282 |
+
for
|
| 283 |
+
un
|
| 284 |
+
##led
|
| 285 |
+
grid
|
| 286 |
+
##eet
|
| 287 |
+
##us
|
| 288 |
+
part
|
| 289 |
+
##2o
|
| 290 |
+
##yd
|
| 291 |
+
##est
|
| 292 |
+
##old
|
| 293 |
+
by
|
| 294 |
+
##co
|
| 295 |
+
oil
|
| 296 |
+
##ce
|
| 297 |
+
##eight
|
| 298 |
+
bo
|
| 299 |
+
##rox
|
| 300 |
+
res
|
| 301 |
+
##gy
|
| 302 |
+
##ss
|
| 303 |
+
##aw
|
| 304 |
+
sheet
|
| 305 |
+
h2o
|
| 306 |
+
us
|
| 307 |
+
##ly
|
| 308 |
+
with
|
| 309 |
+
##esel
|
| 310 |
+
transp
|
| 311 |
+
capacity
|
| 312 |
+
mo
|
| 313 |
+
##iner
|
| 314 |
+
transport
|
| 315 |
+
##uro
|
| 316 |
+
weight
|
| 317 |
+
##iz
|
| 318 |
+
),
|
| 319 |
+
##bon
|
| 320 |
+
bi
|
| 321 |
+
on
|
| 322 |
+
##ergy
|
| 323 |
+
diesel
|
| 324 |
+
energy
|
| 325 |
+
euro
|
| 326 |
+
##un
|
| 327 |
+
##lu
|
| 328 |
+
##rect
|
| 329 |
+
##age
|
| 330 |
+
approx
|
| 331 |
+
se
|
| 332 |
+
gross
|
| 333 |
+
carbon
|
| 334 |
+
cr
|
| 335 |
+
##imation
|
| 336 |
+
approximation
|
| 337 |
+
##cy
|
| 338 |
+
##ment
|
| 339 |
+
##fill
|
| 340 |
+
to
|
| 341 |
+
12
|
| 342 |
+
acid
|
| 343 |
+
land
|
| 344 |
+
##umin
|
| 345 |
+
op
|
| 346 |
+
##ug
|
| 347 |
+
##av
|
| 348 |
+
landfill
|
| 349 |
+
##ial
|
| 350 |
+
alumin
|
| 351 |
+
##mm
|
| 352 |
+
##put
|
| 353 |
+
##ural
|
| 354 |
+
allo
|
| 355 |
+
##cess
|
| 356 |
+
fiber
|
| 357 |
+
eth
|
| 358 |
+
powered
|
| 359 |
+
process
|
| 360 |
+
production
|
| 361 |
+
ex
|
| 362 |
+
vd
|
| 363 |
+
##act
|
| 364 |
+
moist
|
| 365 |
+
alloc
|
| 366 |
+
##iv
|
| 367 |
+
##cr
|
| 368 |
+
##ain
|
| 369 |
+
##lor
|
| 370 |
+
##ab
|
| 371 |
+
de
|
| 372 |
+
##mg
|
| 373 |
+
hyd
|
| 374 |
+
kw
|
| 375 |
+
pr
|
| 376 |
+
##ile
|
| 377 |
+
##one
|
| 378 |
+
moisture
|
| 379 |
+
hard
|
| 380 |
+
##amine
|
| 381 |
+
rol
|
| 382 |
+
open
|
| 383 |
+
##os
|
| 384 |
+
##all
|
| 385 |
+
te
|
| 386 |
+
##ne
|
| 387 |
+
##iler
|
| 388 |
+
##con
|
| 389 |
+
##for
|
| 390 |
+
kg
|
| 391 |
+
##erm
|
| 392 |
+
dri
|
| 393 |
+
input
|
| 394 |
+
comp
|
| 395 |
+
cf
|
| 396 |
+
so
|
| 397 |
+
cem
|
| 398 |
+
##ph
|
| 399 |
+
treat
|
| 400 |
+
treatment
|
| 401 |
+
ag
|
| 402 |
+
lc
|
| 403 |
+
##der
|
| 404 |
+
allocation
|
| 405 |
+
rolled
|
| 406 |
+
flo
|
| 407 |
+
mun
|
| 408 |
+
##icip
|
| 409 |
+
##ctor
|
| 410 |
+
plast
|
| 411 |
+
roof
|
| 412 |
+
municip
|
| 413 |
+
municipal
|
| 414 |
+
10
|
| 415 |
+
cold
|
| 416 |
+
##ay
|
| 417 |
+
##pe
|
| 418 |
+
##verage
|
| 419 |
+
average
|
| 420 |
+
##cycl
|
| 421 |
+
recycl
|
| 422 |
+
dried
|
| 423 |
+
meth
|
| 424 |
+
wood
|
| 425 |
+
ep
|
| 426 |
+
nat
|
| 427 |
+
##br
|
| 428 |
+
##og
|
| 429 |
+
60
|
| 430 |
+
##ance
|
| 431 |
+
201
|
| 432 |
+
natural
|
| 433 |
+
steam
|
| 434 |
+
aluminium
|
| 435 |
+
##ite
|
| 436 |
+
therm
|
| 437 |
+
high
|
| 438 |
+
wh
|
| 439 |
+
##di
|
| 440 |
+
##sion
|
| 441 |
+
reg
|
| 442 |
+
##ot
|
| 443 |
+
14
|
| 444 |
+
##bo
|
| 445 |
+
##uel
|
| 446 |
+
pan
|
| 447 |
+
ply
|
| 448 |
+
fuel
|
| 449 |
+
hydro
|
| 450 |
+
ha
|
| 451 |
+
mod
|
| 452 |
+
sol
|
| 453 |
+
##ir
|
| 454 |
+
##lass
|
| 455 |
+
##ub
|
| 456 |
+
##ust
|
| 457 |
+
conne
|
| 458 |
+
connector
|
| 459 |
+
c3
|
| 460 |
+
lum
|
| 461 |
+
inc
|
| 462 |
+
chlor
|
| 463 |
+
region
|
| 464 |
+
eg
|
| 465 |
+
sof
|
| 466 |
+
##ry
|
| 467 |
+
##sul
|
| 468 |
+
coated
|
| 469 |
+
floor
|
| 470 |
+
soft
|
| 471 |
+
cor
|
| 472 |
+
light
|
| 473 |
+
comb
|
| 474 |
+
board
|
| 475 |
+
lumber
|
| 476 |
+
c4
|
| 477 |
+
##kv
|
| 478 |
+
kil
|
| 479 |
+
mel
|
| 480 |
+
kiln
|
| 481 |
+
bf
|
| 482 |
+
coat
|
| 483 |
+
a5
|
| 484 |
+
recycling
|
| 485 |
+
##x1
|
| 486 |
+
##ical
|
| 487 |
+
inciner
|
| 488 |
+
##mer
|
| 489 |
+
haul
|
| 490 |
+
##ens
|
| 491 |
+
##ode
|
| 492 |
+
cut
|
| 493 |
+
fl
|
| 494 |
+
he
|
| 495 |
+
pet
|
| 496 |
+
up
|
| 497 |
+
##anul
|
| 498 |
+
direct
|
| 499 |
+
granul
|
| 500 |
+
incineration
|
| 501 |
+
heat
|
| 502 |
+
melamine
|
| 503 |
+
but
|
| 504 |
+
softwood
|
| 505 |
+
rene
|
| 506 |
+
insul
|
| 507 |
+
200
|
| 508 |
+
vda
|
| 509 |
+
cement
|
| 510 |
+
renew
|
| 511 |
+
e1
|
| 512 |
+
##ethane
|
| 513 |
+
15
|
| 514 |
+
pin
|
| 515 |
+
##uf
|
| 516 |
+
##dust
|
| 517 |
+
25
|
| 518 |
+
hd
|
| 519 |
+
sm
|
| 520 |
+
sy
|
| 521 |
+
slu
|
| 522 |
+
##ia
|
| 523 |
+
##op
|
| 524 |
+
##dge
|
| 525 |
+
##yp
|
| 526 |
+
##int
|
| 527 |
+
##ingle
|
| 528 |
+
dist
|
| 529 |
+
roofing
|
| 530 |
+
granulate
|
| 531 |
+
sludge
|
| 532 |
+
mill
|
| 533 |
+
sp
|
| 534 |
+
##ding
|
| 535 |
+
electr
|
| 536 |
+
##board
|
| 537 |
+
##if
|
| 538 |
+
##ue
|
| 539 |
+
##ong
|
| 540 |
+
flooring
|
| 541 |
+
22
|
| 542 |
+
fo
|
| 543 |
+
pe
|
| 544 |
+
##infor
|
| 545 |
+
reinfor
|
| 546 |
+
reinforc
|
| 547 |
+
##ied
|
| 548 |
+
##ox
|
| 549 |
+
##tr
|
| 550 |
+
mem
|
| 551 |
+
##ive
|
| 552 |
+
nm
|
| 553 |
+
single
|
| 554 |
+
##per
|
| 555 |
+
##fin
|
| 556 |
+
##icle
|
| 557 |
+
incl
|
| 558 |
+
##sph
|
| 559 |
+
tex
|
| 560 |
+
plywood
|
| 561 |
+
model
|
| 562 |
+
18
|
| 563 |
+
16
|
| 564 |
+
man
|
| 565 |
+
ph
|
| 566 |
+
saw
|
| 567 |
+
##oline
|
| 568 |
+
indi
|
| 569 |
+
gasoline
|
| 570 |
+
indirect
|
| 571 |
+
dw
|
| 572 |
+
##yr
|
| 573 |
+
##ete
|
| 574 |
+
##ell
|
| 575 |
+
resist
|
| 576 |
+
hardwood
|
| 577 |
+
sil
|
| 578 |
+
##anol
|
| 579 |
+
ba
|
| 580 |
+
coating
|
| 581 |
+
000
|
| 582 |
+
pip
|
| 583 |
+
##ool
|
| 584 |
+
boiler
|
| 585 |
+
sul
|
| 586 |
+
indust
|
| 587 |
+
membr
|
| 588 |
+
##ous
|
| 589 |
+
##ides
|
| 590 |
+
##crete
|
| 591 |
+
membrane
|
| 592 |
+
resin
|
| 593 |
+
insulation
|
| 594 |
+
32
|
| 595 |
+
econ
|
| 596 |
+
ic
|
| 597 |
+
econom
|
| 598 |
+
pv
|
| 599 |
+
##ru
|
| 600 |
+
##hyd
|