Commit
·
e1c43e1
1
Parent(s):
ae48b9d
Upload tokenizer
Browse files- special_tokens_map.json +4 -0
- tokenizer.json +861 -0
- tokenizer_config.json +8 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token": "<end>",
|
| 3 |
+
"pad_token": "<pad>"
|
| 4 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,861 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
{
|
| 7 |
+
"id": 0,
|
| 8 |
+
"content": "<start>",
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"special": true
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"id": 1,
|
| 17 |
+
"content": "<end>",
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"special": true
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"id": 2,
|
| 26 |
+
"content": "<pad>",
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"special": true
|
| 32 |
+
}
|
| 33 |
+
],
|
| 34 |
+
"normalizer": null,
|
| 35 |
+
"pre_tokenizer": {
|
| 36 |
+
"type": "ByteLevel",
|
| 37 |
+
"add_prefix_space": false,
|
| 38 |
+
"trim_offsets": true,
|
| 39 |
+
"use_regex": true
|
| 40 |
+
},
|
| 41 |
+
"post_processor": {
|
| 42 |
+
"type": "ByteLevel",
|
| 43 |
+
"add_prefix_space": true,
|
| 44 |
+
"trim_offsets": false,
|
| 45 |
+
"use_regex": true
|
| 46 |
+
},
|
| 47 |
+
"decoder": {
|
| 48 |
+
"type": "ByteLevel",
|
| 49 |
+
"add_prefix_space": true,
|
| 50 |
+
"trim_offsets": true,
|
| 51 |
+
"use_regex": true
|
| 52 |
+
},
|
| 53 |
+
"model": {
|
| 54 |
+
"type": "BPE",
|
| 55 |
+
"dropout": null,
|
| 56 |
+
"unk_token": null,
|
| 57 |
+
"continuing_subword_prefix": null,
|
| 58 |
+
"end_of_word_suffix": null,
|
| 59 |
+
"fuse_unk": false,
|
| 60 |
+
"byte_fallback": false,
|
| 61 |
+
"vocab": {
|
| 62 |
+
"<start>": 0,
|
| 63 |
+
"<end>": 1,
|
| 64 |
+
"<pad>": 2,
|
| 65 |
+
"-": 3,
|
| 66 |
+
".": 4,
|
| 67 |
+
"1": 5,
|
| 68 |
+
"2": 6,
|
| 69 |
+
"3": 7,
|
| 70 |
+
"<": 8,
|
| 71 |
+
">": 9,
|
| 72 |
+
"A": 10,
|
| 73 |
+
"B": 11,
|
| 74 |
+
"C": 12,
|
| 75 |
+
"D": 13,
|
| 76 |
+
"E": 14,
|
| 77 |
+
"F": 15,
|
| 78 |
+
"G": 16,
|
| 79 |
+
"I": 17,
|
| 80 |
+
"J": 18,
|
| 81 |
+
"L": 19,
|
| 82 |
+
"M": 20,
|
| 83 |
+
"N": 21,
|
| 84 |
+
"O": 22,
|
| 85 |
+
"P": 23,
|
| 86 |
+
"R": 24,
|
| 87 |
+
"S": 25,
|
| 88 |
+
"T": 26,
|
| 89 |
+
"U": 27,
|
| 90 |
+
"V": 28,
|
| 91 |
+
"W": 29,
|
| 92 |
+
"X": 30,
|
| 93 |
+
"Z": 31,
|
| 94 |
+
"a": 32,
|
| 95 |
+
"b": 33,
|
| 96 |
+
"c": 34,
|
| 97 |
+
"d": 35,
|
| 98 |
+
"e": 36,
|
| 99 |
+
"f": 37,
|
| 100 |
+
"g": 38,
|
| 101 |
+
"h": 39,
|
| 102 |
+
"i": 40,
|
| 103 |
+
"k": 41,
|
| 104 |
+
"l": 42,
|
| 105 |
+
"m": 43,
|
| 106 |
+
"n": 44,
|
| 107 |
+
"o": 45,
|
| 108 |
+
"p": 46,
|
| 109 |
+
"r": 47,
|
| 110 |
+
"s": 48,
|
| 111 |
+
"t": 49,
|
| 112 |
+
"u": 50,
|
| 113 |
+
"v": 51,
|
| 114 |
+
"w": 52,
|
| 115 |
+
"y": 53,
|
| 116 |
+
"Ġ": 54,
|
| 117 |
+
"ar": 55,
|
| 118 |
+
"nd": 56,
|
| 119 |
+
"st": 57,
|
| 120 |
+
"art": 58,
|
| 121 |
+
"end": 59,
|
| 122 |
+
"Ġ<": 60,
|
| 123 |
+
"start": 61,
|
| 124 |
+
"CN": 62,
|
| 125 |
+
"II": 63,
|
| 126 |
+
"ĠC": 64,
|
| 127 |
+
"CNJ": 65,
|
| 128 |
+
"ĠCCNJ": 66,
|
| 129 |
+
"SG": 67,
|
| 130 |
+
"ĠL": 68,
|
| 131 |
+
"OC": 69,
|
| 132 |
+
"ou": 70,
|
| 133 |
+
"ĠI": 71,
|
| 134 |
+
"on": 72,
|
| 135 |
+
"PL": 73,
|
| 136 |
+
"ĠP": 74,
|
| 137 |
+
"ĠLOC": 75,
|
| 138 |
+
"ho": 76,
|
| 139 |
+
"Ġg": 77,
|
| 140 |
+
"Ġs": 78,
|
| 141 |
+
"in": 79,
|
| 142 |
+
"AS": 80,
|
| 143 |
+
"Ġgo": 81,
|
| 144 |
+
"ĠN": 82,
|
| 145 |
+
"ĠD": 83,
|
| 146 |
+
"Ġw": 84,
|
| 147 |
+
"ĠPR": 85,
|
| 148 |
+
"Ġt": 86,
|
| 149 |
+
"ĠIN": 87,
|
| 150 |
+
"Ġ1": 88,
|
| 151 |
+
"Ġp": 89,
|
| 152 |
+
"SP": 90,
|
| 153 |
+
"MP": 91,
|
| 154 |
+
"OMP": 92,
|
| 155 |
+
"ĠCOMP": 93,
|
| 156 |
+
"Ġh": 94,
|
| 157 |
+
"TR": 95,
|
| 158 |
+
"EP": 96,
|
| 159 |
+
"le": 97,
|
| 160 |
+
"ck": 98,
|
| 161 |
+
"Ġl": 99,
|
| 162 |
+
"OSP": 100,
|
| 163 |
+
"ĠPROSP": 101,
|
| 164 |
+
"ke": 102,
|
| 165 |
+
"ll": 103,
|
| 166 |
+
"se": 104,
|
| 167 |
+
"ID": 105,
|
| 168 |
+
"re": 106,
|
| 169 |
+
"Ġar": 107,
|
| 170 |
+
"VB": 108,
|
| 171 |
+
"ĠLVB": 109,
|
| 172 |
+
"ay": 110,
|
| 173 |
+
"Ġin": 111,
|
| 174 |
+
"out": 112,
|
| 175 |
+
"CCNJ": 113,
|
| 176 |
+
"or": 114,
|
| 177 |
+
"CEP": 115,
|
| 178 |
+
"ĠINCEP": 116,
|
| 179 |
+
"EG": 117,
|
| 180 |
+
"FOC": 118,
|
| 181 |
+
"te": 119,
|
| 182 |
+
"ĠNEG": 120,
|
| 183 |
+
"ake": 121,
|
| 184 |
+
"ound": 122,
|
| 185 |
+
"Ġaround": 123,
|
| 186 |
+
"WID": 124,
|
| 187 |
+
"Ġf": 125,
|
| 188 |
+
"ĠDWID": 126,
|
| 189 |
+
"Ġon": 127,
|
| 190 |
+
"PAS": 128,
|
| 191 |
+
"me": 129,
|
| 192 |
+
"PASS": 130,
|
| 193 |
+
"an": 131,
|
| 194 |
+
"ee": 132,
|
| 195 |
+
"pe": 133,
|
| 196 |
+
"EAS": 134,
|
| 197 |
+
"REAS": 135,
|
| 198 |
+
"Ġb": 136,
|
| 199 |
+
"ĠREAS": 137,
|
| 200 |
+
"ouse": 138,
|
| 201 |
+
"Ġpi": 139,
|
| 202 |
+
"ĠS": 140,
|
| 203 |
+
"co": 141,
|
| 204 |
+
"LZ": 142,
|
| 205 |
+
"MLZ": 143,
|
| 206 |
+
"ĠNMLZ": 144,
|
| 207 |
+
"ork": 145,
|
| 208 |
+
"it": 146,
|
| 209 |
+
"Ġm": 147,
|
| 210 |
+
"BL": 148,
|
| 211 |
+
"FV": 149,
|
| 212 |
+
"OBL": 150,
|
| 213 |
+
"PFV": 151,
|
| 214 |
+
"ĠIPFV": 152,
|
| 215 |
+
"AN": 153,
|
| 216 |
+
"mp": 154,
|
| 217 |
+
"to": 155,
|
| 218 |
+
"Ġwho": 156,
|
| 219 |
+
"Ġhouse": 157,
|
| 220 |
+
"Ġpipe": 158,
|
| 221 |
+
"comp": 159,
|
| 222 |
+
"Ġhit": 160,
|
| 223 |
+
"ac": 161,
|
| 224 |
+
"ain": 162,
|
| 225 |
+
"all": 163,
|
| 226 |
+
"Ġtr": 164,
|
| 227 |
+
"ĠINS": 165,
|
| 228 |
+
"ear": 166,
|
| 229 |
+
"ow": 167,
|
| 230 |
+
"oll": 168,
|
| 231 |
+
"Ġtake": 169,
|
| 232 |
+
"Ġfoll": 170,
|
| 233 |
+
"Ġfollow": 171,
|
| 234 |
+
"RR": 172,
|
| 235 |
+
"Ġout": 173,
|
| 236 |
+
"AU": 174,
|
| 237 |
+
"ĠOBL": 175,
|
| 238 |
+
"AUS": 176,
|
| 239 |
+
"ri": 177,
|
| 240 |
+
"ong": 178,
|
| 241 |
+
"SX": 179,
|
| 242 |
+
"ack": 180,
|
| 243 |
+
"lm": 181,
|
| 244 |
+
"ve": 182,
|
| 245 |
+
"Ġo": 183,
|
| 246 |
+
"holm": 184,
|
| 247 |
+
"Ġsee": 185,
|
| 248 |
+
"ckholm": 186,
|
| 249 |
+
"ĠSto": 187,
|
| 250 |
+
"ĠStockholm": 188,
|
| 251 |
+
"CAUS": 189,
|
| 252 |
+
"IP": 190,
|
| 253 |
+
"TIP": 191,
|
| 254 |
+
"ly": 192,
|
| 255 |
+
"od": 193,
|
| 256 |
+
"par": 194,
|
| 257 |
+
"Ġcomp": 195,
|
| 258 |
+
"Ġgood": 196,
|
| 259 |
+
"Ġwork": 197,
|
| 260 |
+
"Ġth": 198,
|
| 261 |
+
"lete": 199,
|
| 262 |
+
"ANTIP": 200,
|
| 263 |
+
"Ġcomplete": 201,
|
| 264 |
+
"Ġcompletely": 202,
|
| 265 |
+
"ER": 203,
|
| 266 |
+
"VER": 204,
|
| 267 |
+
"ĠVER": 205,
|
| 268 |
+
"Ġsay": 206,
|
| 269 |
+
"DM": 207,
|
| 270 |
+
"IS": 208,
|
| 271 |
+
"he": 209,
|
| 272 |
+
"ir": 210,
|
| 273 |
+
"rn": 211,
|
| 274 |
+
"rt": 212,
|
| 275 |
+
"tu": 213,
|
| 276 |
+
"Ġ3": 214,
|
| 277 |
+
"III": 215,
|
| 278 |
+
"hort": 216,
|
| 279 |
+
"Ġshort": 217,
|
| 280 |
+
"Ġli": 218,
|
| 281 |
+
"Ġmake": 219,
|
| 282 |
+
"Ġtry": 220,
|
| 283 |
+
"turn": 221,
|
| 284 |
+
"ab": 222,
|
| 285 |
+
"un": 223,
|
| 286 |
+
"Ġlay": 224,
|
| 287 |
+
"able": 225,
|
| 288 |
+
"AR": 226,
|
| 289 |
+
"ca": 227,
|
| 290 |
+
"do": 228,
|
| 291 |
+
"way": 229,
|
| 292 |
+
"Ġdo": 230,
|
| 293 |
+
"ĠIRR": 231,
|
| 294 |
+
"ĠPAR": 232,
|
| 295 |
+
"SPT": 233,
|
| 296 |
+
"Ġdoor": 234,
|
| 297 |
+
"ĠPART": 235,
|
| 298 |
+
"DE": 236,
|
| 299 |
+
"OX": 237,
|
| 300 |
+
"PR": 238,
|
| 301 |
+
"work": 239,
|
| 302 |
+
"Ġre": 240,
|
| 303 |
+
"home": 241,
|
| 304 |
+
"Ġwh": 242,
|
| 305 |
+
"DEM": 243,
|
| 306 |
+
"PROX": 244,
|
| 307 |
+
"ate": 245,
|
| 308 |
+
"no": 246,
|
| 309 |
+
"so": 247,
|
| 310 |
+
"Ġno": 248,
|
| 311 |
+
"rive": 249,
|
| 312 |
+
"Ġnot": 250,
|
| 313 |
+
"Ġlong": 251,
|
| 314 |
+
"Ġlack": 252,
|
| 315 |
+
"PN": 253,
|
| 316 |
+
"AX": 254,
|
| 317 |
+
"EL": 255,
|
| 318 |
+
"EV": 256,
|
| 319 |
+
"IRR": 257,
|
| 320 |
+
"MAN": 258,
|
| 321 |
+
"ad": 259,
|
| 322 |
+
"ag": 260,
|
| 323 |
+
"at": 261,
|
| 324 |
+
"con": 262,
|
| 325 |
+
"de": 263,
|
| 326 |
+
"ike": 264,
|
| 327 |
+
"ian": 265,
|
| 328 |
+
"ide": 266,
|
| 329 |
+
"long": 267,
|
| 330 |
+
"like": 268,
|
| 331 |
+
"mall": 269,
|
| 332 |
+
"os": 270,
|
| 333 |
+
"ole": 271,
|
| 334 |
+
"pre": 272,
|
| 335 |
+
"pouse": 273,
|
| 336 |
+
"ros": 274,
|
| 337 |
+
"side": 275,
|
| 338 |
+
"tin": 276,
|
| 339 |
+
"uall": 277,
|
| 340 |
+
"year": 278,
|
| 341 |
+
"ĠCN": 279,
|
| 342 |
+
"Ġho": 280,
|
| 343 |
+
"Ġac": 281,
|
| 344 |
+
"ĠAX": 282,
|
| 345 |
+
"Ġcon": 283,
|
| 346 |
+
"Ġyear": 284,
|
| 347 |
+
"ĠCan": 285,
|
| 348 |
+
"ĠPCNJ": 286,
|
| 349 |
+
"Ġgir": 287,
|
| 350 |
+
"Ġsmall": 288,
|
| 351 |
+
"Ġspouse": 289,
|
| 352 |
+
"ĠDM": 290,
|
| 353 |
+
"ĠDIS": 291,
|
| 354 |
+
"Ġwee": 292,
|
| 355 |
+
"Ġpee": 293,
|
| 356 |
+
"Ġpole": 294,
|
| 357 |
+
"ree": 295,
|
| 358 |
+
"rest": 296,
|
| 359 |
+
"Ġinside": 297,
|
| 360 |
+
"any": 298,
|
| 361 |
+
"Ġpick": 299,
|
| 362 |
+
"ĠSEL": 300,
|
| 363 |
+
"Ġman": 301,
|
| 364 |
+
"company": 302,
|
| 365 |
+
"acros": 303,
|
| 366 |
+
"Ġtrain": 304,
|
| 367 |
+
"pare": 305,
|
| 368 |
+
"Ġthree": 306,
|
| 369 |
+
"heart": 307,
|
| 370 |
+
"Ġlie": 308,
|
| 371 |
+
"case": 309,
|
| 372 |
+
"Ġreturn": 310,
|
| 373 |
+
"Ġwhat": 311,
|
| 374 |
+
"EVID": 312,
|
| 375 |
+
"MANR": 313,
|
| 376 |
+
"adian": 314,
|
| 377 |
+
"again": 315,
|
| 378 |
+
"prepare": 316,
|
| 379 |
+
"tinuall": 317,
|
| 380 |
+
"ĠCNTR": 318,
|
| 381 |
+
"Ġhole": 319,
|
| 382 |
+
"Ġaccompany": 320,
|
| 383 |
+
"Ġcontinuall": 321,
|
| 384 |
+
"ĠCanadian": 322,
|
| 385 |
+
"Ġgirl": 323,
|
| 386 |
+
"ĠDISTR": 324,
|
| 387 |
+
"Ġweek": 325,
|
| 388 |
+
"ĠSELF": 326,
|
| 389 |
+
"across": 327,
|
| 390 |
+
"Ġcontinually": 328,
|
| 391 |
+
"ES": 329,
|
| 392 |
+
"ak": 330,
|
| 393 |
+
"eri": 331,
|
| 394 |
+
"epar": 332,
|
| 395 |
+
"gh": 333,
|
| 396 |
+
"ig": 334,
|
| 397 |
+
"ind": 335,
|
| 398 |
+
"Ġun": 336,
|
| 399 |
+
"ough": 337,
|
| 400 |
+
"Ġsepar": 338,
|
| 401 |
+
"ĠDES": 339,
|
| 402 |
+
"Ġperi": 340,
|
| 403 |
+
"Ġhear": 341,
|
| 404 |
+
"reak": 342,
|
| 405 |
+
"Ġarrive": 343,
|
| 406 |
+
"ter": 344,
|
| 407 |
+
"Ġfind": 345,
|
| 408 |
+
"Ġone": 346,
|
| 409 |
+
"meter": 347,
|
| 410 |
+
"Ġback": 348,
|
| 411 |
+
"Ġbig": 349,
|
| 412 |
+
"Ġbreak": 350,
|
| 413 |
+
"Ġoh": 351,
|
| 414 |
+
"Ġthough": 352,
|
| 415 |
+
"Ġunable": 353,
|
| 416 |
+
"Ġseparate": 354,
|
| 417 |
+
"Ġperimeter": 355,
|
| 418 |
+
"Ġthought": 356,
|
| 419 |
+
"fir": 357,
|
| 420 |
+
"ime": 358,
|
| 421 |
+
"lo": 359,
|
| 422 |
+
"pain": 360,
|
| 423 |
+
"run": 361,
|
| 424 |
+
"the": 362,
|
| 425 |
+
"time": 363,
|
| 426 |
+
"Ġco": 364,
|
| 427 |
+
"Ġall": 365,
|
| 428 |
+
"ĠSPT": 366,
|
| 429 |
+
"Ġrun": 367,
|
| 430 |
+
"ĠPREP": 368,
|
| 431 |
+
"EPIS": 369,
|
| 432 |
+
"Ġfear": 370,
|
| 433 |
+
"pen": 371,
|
| 434 |
+
"Ġblo": 372,
|
| 435 |
+
"ĠSpain": 373,
|
| 436 |
+
"Ġopen": 374,
|
| 437 |
+
"Ġlive": 375,
|
| 438 |
+
"first": 376,
|
| 439 |
+
"Ġcome": 377,
|
| 440 |
+
"Ġblock": 378,
|
| 441 |
+
"eca": 379,
|
| 442 |
+
"use": 380,
|
| 443 |
+
"Ġbeca": 381,
|
| 444 |
+
"Ġbecause": 382,
|
| 445 |
+
"AL": 383,
|
| 446 |
+
"BM": 384,
|
| 447 |
+
"VAL": 385,
|
| 448 |
+
"ai": 386,
|
| 449 |
+
"as": 387,
|
| 450 |
+
"ame": 388,
|
| 451 |
+
"ce": 389,
|
| 452 |
+
"en": 390,
|
| 453 |
+
"ep": 391,
|
| 454 |
+
"ff": 392,
|
| 455 |
+
"ite": 393,
|
| 456 |
+
"ice": 394,
|
| 457 |
+
"lac": 395,
|
| 458 |
+
"mar": 396,
|
| 459 |
+
"name": 397,
|
| 460 |
+
"prive": 398,
|
| 461 |
+
"rs": 399,
|
| 462 |
+
"sit": 400,
|
| 463 |
+
"uprive": 401,
|
| 464 |
+
"was": 402,
|
| 465 |
+
"ĠCAUS": 403,
|
| 466 |
+
"ĠIBM": 404,
|
| 467 |
+
"Ġsle": 405,
|
| 468 |
+
"ĠDen": 406,
|
| 469 |
+
"Ġwate": 407,
|
| 470 |
+
"Ġplac": 408,
|
| 471 |
+
"pers": 409,
|
| 472 |
+
"Ġmai": 410,
|
| 473 |
+
"ach": 411,
|
| 474 |
+
"Ġoff": 412,
|
| 475 |
+
"Ġreach": 413,
|
| 476 |
+
"Ġwhite": 414,
|
| 477 |
+
"mark": 415,
|
| 478 |
+
"upriver": 416,
|
| 479 |
+
"wash": 417,
|
| 480 |
+
"Ġsleep": 418,
|
| 481 |
+
"ĠDenmark": 419,
|
| 482 |
+
"Ġwater": 420,
|
| 483 |
+
"Ġplace": 421,
|
| 484 |
+
"person": 422,
|
| 485 |
+
"Ġmail": 423,
|
| 486 |
+
"Ġoffice": 424
|
| 487 |
+
},
|
| 488 |
+
"merges": [
|
| 489 |
+
"a r",
|
| 490 |
+
"n d",
|
| 491 |
+
"s t",
|
| 492 |
+
"ar t",
|
| 493 |
+
"e nd",
|
| 494 |
+
"Ġ <",
|
| 495 |
+
"st art",
|
| 496 |
+
"C N",
|
| 497 |
+
"I I",
|
| 498 |
+
"Ġ C",
|
| 499 |
+
"CN J",
|
| 500 |
+
"ĠC CNJ",
|
| 501 |
+
"S G",
|
| 502 |
+
"Ġ L",
|
| 503 |
+
"O C",
|
| 504 |
+
"o u",
|
| 505 |
+
"Ġ I",
|
| 506 |
+
"o n",
|
| 507 |
+
"P L",
|
| 508 |
+
"Ġ P",
|
| 509 |
+
"ĠL OC",
|
| 510 |
+
"h o",
|
| 511 |
+
"Ġ g",
|
| 512 |
+
"Ġ s",
|
| 513 |
+
"i n",
|
| 514 |
+
"A S",
|
| 515 |
+
"Ġg o",
|
| 516 |
+
"Ġ N",
|
| 517 |
+
"Ġ D",
|
| 518 |
+
"Ġ w",
|
| 519 |
+
"ĠP R",
|
| 520 |
+
"Ġ t",
|
| 521 |
+
"ĠI N",
|
| 522 |
+
"Ġ 1",
|
| 523 |
+
"Ġ p",
|
| 524 |
+
"S P",
|
| 525 |
+
"M P",
|
| 526 |
+
"O MP",
|
| 527 |
+
"ĠC OMP",
|
| 528 |
+
"Ġ h",
|
| 529 |
+
"T R",
|
| 530 |
+
"E P",
|
| 531 |
+
"l e",
|
| 532 |
+
"c k",
|
| 533 |
+
"Ġ l",
|
| 534 |
+
"O SP",
|
| 535 |
+
"ĠPR OSP",
|
| 536 |
+
"k e",
|
| 537 |
+
"l l",
|
| 538 |
+
"s e",
|
| 539 |
+
"I D",
|
| 540 |
+
"r e",
|
| 541 |
+
"Ġ ar",
|
| 542 |
+
"V B",
|
| 543 |
+
"ĠL VB",
|
| 544 |
+
"a y",
|
| 545 |
+
"Ġ in",
|
| 546 |
+
"ou t",
|
| 547 |
+
"C CNJ",
|
| 548 |
+
"o r",
|
| 549 |
+
"C EP",
|
| 550 |
+
"ĠIN CEP",
|
| 551 |
+
"E G",
|
| 552 |
+
"F OC",
|
| 553 |
+
"t e",
|
| 554 |
+
"ĠN EG",
|
| 555 |
+
"a ke",
|
| 556 |
+
"ou nd",
|
| 557 |
+
"Ġar ound",
|
| 558 |
+
"W ID",
|
| 559 |
+
"Ġ f",
|
| 560 |
+
"ĠD WID",
|
| 561 |
+
"Ġ on",
|
| 562 |
+
"P AS",
|
| 563 |
+
"m e",
|
| 564 |
+
"PAS S",
|
| 565 |
+
"a n",
|
| 566 |
+
"e e",
|
| 567 |
+
"p e",
|
| 568 |
+
"E AS",
|
| 569 |
+
"R EAS",
|
| 570 |
+
"Ġ b",
|
| 571 |
+
"Ġ REAS",
|
| 572 |
+
"ou se",
|
| 573 |
+
"Ġp i",
|
| 574 |
+
"Ġ S",
|
| 575 |
+
"c o",
|
| 576 |
+
"L Z",
|
| 577 |
+
"M LZ",
|
| 578 |
+
"ĠN MLZ",
|
| 579 |
+
"or k",
|
| 580 |
+
"i t",
|
| 581 |
+
"Ġ m",
|
| 582 |
+
"B L",
|
| 583 |
+
"F V",
|
| 584 |
+
"O BL",
|
| 585 |
+
"P FV",
|
| 586 |
+
"ĠI PFV",
|
| 587 |
+
"A N",
|
| 588 |
+
"m p",
|
| 589 |
+
"t o",
|
| 590 |
+
"Ġw ho",
|
| 591 |
+
"Ġh ouse",
|
| 592 |
+
"Ġpi pe",
|
| 593 |
+
"co mp",
|
| 594 |
+
"Ġh it",
|
| 595 |
+
"a c",
|
| 596 |
+
"a in",
|
| 597 |
+
"a ll",
|
| 598 |
+
"Ġt r",
|
| 599 |
+
"ĠIN S",
|
| 600 |
+
"e ar",
|
| 601 |
+
"o w",
|
| 602 |
+
"o ll",
|
| 603 |
+
"Ġt ake",
|
| 604 |
+
"Ġf oll",
|
| 605 |
+
"Ġfoll ow",
|
| 606 |
+
"R R",
|
| 607 |
+
"Ġ out",
|
| 608 |
+
"A U",
|
| 609 |
+
"Ġ OBL",
|
| 610 |
+
"AU S",
|
| 611 |
+
"r i",
|
| 612 |
+
"on g",
|
| 613 |
+
"S X",
|
| 614 |
+
"a ck",
|
| 615 |
+
"l m",
|
| 616 |
+
"v e",
|
| 617 |
+
"Ġ o",
|
| 618 |
+
"ho lm",
|
| 619 |
+
"Ġs ee",
|
| 620 |
+
"ck holm",
|
| 621 |
+
"ĠS to",
|
| 622 |
+
"ĠSto ckholm",
|
| 623 |
+
"C AUS",
|
| 624 |
+
"I P",
|
| 625 |
+
"T IP",
|
| 626 |
+
"l y",
|
| 627 |
+
"o d",
|
| 628 |
+
"p ar",
|
| 629 |
+
"Ġ comp",
|
| 630 |
+
"Ġgo od",
|
| 631 |
+
"Ġw ork",
|
| 632 |
+
"Ġt h",
|
| 633 |
+
"le te",
|
| 634 |
+
"AN TIP",
|
| 635 |
+
"Ġcomp lete",
|
| 636 |
+
"Ġcomplete ly",
|
| 637 |
+
"E R",
|
| 638 |
+
"V ER",
|
| 639 |
+
"Ġ VER",
|
| 640 |
+
"Ġs ay",
|
| 641 |
+
"D M",
|
| 642 |
+
"I S",
|
| 643 |
+
"h e",
|
| 644 |
+
"i r",
|
| 645 |
+
"r n",
|
| 646 |
+
"r t",
|
| 647 |
+
"t u",
|
| 648 |
+
"Ġ 3",
|
| 649 |
+
"II I",
|
| 650 |
+
"ho rt",
|
| 651 |
+
"Ġs hort",
|
| 652 |
+
"Ġl i",
|
| 653 |
+
"Ġm ake",
|
| 654 |
+
"Ġtr y",
|
| 655 |
+
"tu rn",
|
| 656 |
+
"a b",
|
| 657 |
+
"u n",
|
| 658 |
+
"Ġl ay",
|
| 659 |
+
"ab le",
|
| 660 |
+
"A R",
|
| 661 |
+
"c a",
|
| 662 |
+
"d o",
|
| 663 |
+
"w ay",
|
| 664 |
+
"Ġ do",
|
| 665 |
+
"ĠI RR",
|
| 666 |
+
"ĠP AR",
|
| 667 |
+
"SP T",
|
| 668 |
+
"Ġdo or",
|
| 669 |
+
"ĠPAR T",
|
| 670 |
+
"D E",
|
| 671 |
+
"O X",
|
| 672 |
+
"P R",
|
| 673 |
+
"w ork",
|
| 674 |
+
"Ġ re",
|
| 675 |
+
"ho me",
|
| 676 |
+
"Ġw h",
|
| 677 |
+
"DE M",
|
| 678 |
+
"PR OX",
|
| 679 |
+
"a te",
|
| 680 |
+
"n o",
|
| 681 |
+
"s o",
|
| 682 |
+
"Ġ no",
|
| 683 |
+
"ri ve",
|
| 684 |
+
"Ġno t",
|
| 685 |
+
"Ġl ong",
|
| 686 |
+
"Ġl ack",
|
| 687 |
+
"P N",
|
| 688 |
+
"A X",
|
| 689 |
+
"E L",
|
| 690 |
+
"E V",
|
| 691 |
+
"I RR",
|
| 692 |
+
"M AN",
|
| 693 |
+
"a d",
|
| 694 |
+
"a g",
|
| 695 |
+
"a t",
|
| 696 |
+
"c on",
|
| 697 |
+
"d e",
|
| 698 |
+
"i ke",
|
| 699 |
+
"i an",
|
| 700 |
+
"i de",
|
| 701 |
+
"l ong",
|
| 702 |
+
"l ike",
|
| 703 |
+
"m all",
|
| 704 |
+
"o s",
|
| 705 |
+
"o le",
|
| 706 |
+
"p re",
|
| 707 |
+
"p ouse",
|
| 708 |
+
"r os",
|
| 709 |
+
"s ide",
|
| 710 |
+
"t in",
|
| 711 |
+
"u all",
|
| 712 |
+
"y ear",
|
| 713 |
+
"Ġ CN",
|
| 714 |
+
"Ġ ho",
|
| 715 |
+
"Ġ ac",
|
| 716 |
+
"Ġ AX",
|
| 717 |
+
"Ġ con",
|
| 718 |
+
"Ġ year",
|
| 719 |
+
"ĠC an",
|
| 720 |
+
"ĠP CNJ",
|
| 721 |
+
"Ġg ir",
|
| 722 |
+
"Ġs mall",
|
| 723 |
+
"Ġs pouse",
|
| 724 |
+
"ĠD M",
|
| 725 |
+
"ĠD IS",
|
| 726 |
+
"Ġw ee",
|
| 727 |
+
"Ġp ee",
|
| 728 |
+
"Ġp ole",
|
| 729 |
+
"re e",
|
| 730 |
+
"re st",
|
| 731 |
+
"Ġin side",
|
| 732 |
+
"an y",
|
| 733 |
+
"Ġpi ck",
|
| 734 |
+
"ĠS EL",
|
| 735 |
+
"Ġm an",
|
| 736 |
+
"comp any",
|
| 737 |
+
"ac ros",
|
| 738 |
+
"Ġtr ain",
|
| 739 |
+
"par e",
|
| 740 |
+
"Ġth ree",
|
| 741 |
+
"he art",
|
| 742 |
+
"Ġli e",
|
| 743 |
+
"ca se",
|
| 744 |
+
"Ġre turn",
|
| 745 |
+
"Ġwh at",
|
| 746 |
+
"EV ID",
|
| 747 |
+
"MAN R",
|
| 748 |
+
"ad ian",
|
| 749 |
+
"ag ain",
|
| 750 |
+
"pre pare",
|
| 751 |
+
"tin uall",
|
| 752 |
+
"ĠCN TR",
|
| 753 |
+
"Ġho le",
|
| 754 |
+
"Ġac company",
|
| 755 |
+
"Ġcon tinuall",
|
| 756 |
+
"ĠCan adian",
|
| 757 |
+
"Ġgir l",
|
| 758 |
+
"ĠDIS TR",
|
| 759 |
+
"Ġwee k",
|
| 760 |
+
"ĠSEL F",
|
| 761 |
+
"acros s",
|
| 762 |
+
"Ġcontinuall y",
|
| 763 |
+
"E S",
|
| 764 |
+
"a k",
|
| 765 |
+
"e ri",
|
| 766 |
+
"e par",
|
| 767 |
+
"g h",
|
| 768 |
+
"i g",
|
| 769 |
+
"i nd",
|
| 770 |
+
"Ġ un",
|
| 771 |
+
"ou gh",
|
| 772 |
+
"Ġs epar",
|
| 773 |
+
"ĠD ES",
|
| 774 |
+
"Ġp eri",
|
| 775 |
+
"Ġh ear",
|
| 776 |
+
"re ak",
|
| 777 |
+
"Ġar rive",
|
| 778 |
+
"te r",
|
| 779 |
+
"Ġf ind",
|
| 780 |
+
"Ġon e",
|
| 781 |
+
"me ter",
|
| 782 |
+
"Ġb ack",
|
| 783 |
+
"Ġb ig",
|
| 784 |
+
"Ġb reak",
|
| 785 |
+
"Ġo h",
|
| 786 |
+
"Ġth ough",
|
| 787 |
+
"Ġun able",
|
| 788 |
+
"Ġsepar ate",
|
| 789 |
+
"Ġperi meter",
|
| 790 |
+
"Ġthough t",
|
| 791 |
+
"f ir",
|
| 792 |
+
"i me",
|
| 793 |
+
"l o",
|
| 794 |
+
"p ain",
|
| 795 |
+
"r un",
|
| 796 |
+
"t he",
|
| 797 |
+
"t ime",
|
| 798 |
+
"Ġ co",
|
| 799 |
+
"Ġ all",
|
| 800 |
+
"Ġ SPT",
|
| 801 |
+
"Ġ run",
|
| 802 |
+
"ĠPR EP",
|
| 803 |
+
"EP IS",
|
| 804 |
+
"Ġf ear",
|
| 805 |
+
"pe n",
|
| 806 |
+
"Ġb lo",
|
| 807 |
+
"ĠS pain",
|
| 808 |
+
"Ġo pen",
|
| 809 |
+
"Ġli ve",
|
| 810 |
+
"fir st",
|
| 811 |
+
"Ġco me",
|
| 812 |
+
"Ġblo ck",
|
| 813 |
+
"e ca",
|
| 814 |
+
"u se",
|
| 815 |
+
"Ġb eca",
|
| 816 |
+
"Ġbeca use",
|
| 817 |
+
"A L",
|
| 818 |
+
"B M",
|
| 819 |
+
"V AL",
|
| 820 |
+
"a i",
|
| 821 |
+
"a s",
|
| 822 |
+
"a me",
|
| 823 |
+
"c e",
|
| 824 |
+
"e n",
|
| 825 |
+
"e p",
|
| 826 |
+
"f f",
|
| 827 |
+
"i te",
|
| 828 |
+
"i ce",
|
| 829 |
+
"l ac",
|
| 830 |
+
"m ar",
|
| 831 |
+
"n ame",
|
| 832 |
+
"p rive",
|
| 833 |
+
"r s",
|
| 834 |
+
"s it",
|
| 835 |
+
"u prive",
|
| 836 |
+
"w as",
|
| 837 |
+
"ĠC AUS",
|
| 838 |
+
"ĠI BM",
|
| 839 |
+
"Ġs le",
|
| 840 |
+
"ĠD en",
|
| 841 |
+
"Ġw ate",
|
| 842 |
+
"Ġp lac",
|
| 843 |
+
"pe rs",
|
| 844 |
+
"Ġm ai",
|
| 845 |
+
"ac h",
|
| 846 |
+
"Ġo ff",
|
| 847 |
+
"Ġre ach",
|
| 848 |
+
"Ġwh ite",
|
| 849 |
+
"mar k",
|
| 850 |
+
"uprive r",
|
| 851 |
+
"was h",
|
| 852 |
+
"Ġsle ep",
|
| 853 |
+
"ĠDen mark",
|
| 854 |
+
"Ġwate r",
|
| 855 |
+
"Ġplac e",
|
| 856 |
+
"pers on",
|
| 857 |
+
"Ġmai l",
|
| 858 |
+
"Ġoff ice"
|
| 859 |
+
]
|
| 860 |
+
}
|
| 861 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"clean_up_tokenization_spaces": true,
|
| 3 |
+
"eos_token": "<end>",
|
| 4 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 5 |
+
"pad_token": "<pad>",
|
| 6 |
+
"sos_token": "<start>",
|
| 7 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 8 |
+
}
|