Upload 7 files
Browse files- config.json +24 -0
- generation_config.json +5 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +858 -0
- tokenizer_config.json +13 -0
- vocab.txt +703 -0
config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"BertForMaskedLM"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"classifier_dropout": null,
|
7 |
+
"hidden_act": "gelu",
|
8 |
+
"hidden_dropout_prob": 0.1,
|
9 |
+
"hidden_size": 768,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 3072,
|
12 |
+
"layer_norm_eps": 1e-12,
|
13 |
+
"max_position_embeddings": 512,
|
14 |
+
"model_type": "bert",
|
15 |
+
"num_attention_heads": 12,
|
16 |
+
"num_hidden_layers": 12,
|
17 |
+
"pad_token_id": 0,
|
18 |
+
"position_embedding_type": "absolute",
|
19 |
+
"torch_dtype": "float32",
|
20 |
+
"transformers_version": "4.30.2",
|
21 |
+
"type_vocab_size": 2,
|
22 |
+
"use_cache": true,
|
23 |
+
"vocab_size": 30522
|
24 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"pad_token_id": 0,
|
4 |
+
"transformers_version": "4.30.2"
|
5 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19c02a6a3dbddb144455e461427ca68aa4692869a6992b64ec2117f5d7b6cce8
|
3 |
+
size 438130617
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,858 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 256,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
+
"padding": null,
|
10 |
+
"added_tokens": [
|
11 |
+
{
|
12 |
+
"id": 0,
|
13 |
+
"content": "[PAD]",
|
14 |
+
"single_word": false,
|
15 |
+
"lstrip": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"id": 1,
|
22 |
+
"content": "[UNK]",
|
23 |
+
"single_word": false,
|
24 |
+
"lstrip": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"id": 2,
|
31 |
+
"content": "[CLS]",
|
32 |
+
"single_word": false,
|
33 |
+
"lstrip": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"normalized": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"id": 3,
|
40 |
+
"content": "[SEP]",
|
41 |
+
"single_word": false,
|
42 |
+
"lstrip": false,
|
43 |
+
"rstrip": false,
|
44 |
+
"normalized": false,
|
45 |
+
"special": true
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"id": 4,
|
49 |
+
"content": "[MASK]",
|
50 |
+
"single_word": false,
|
51 |
+
"lstrip": false,
|
52 |
+
"rstrip": false,
|
53 |
+
"normalized": false,
|
54 |
+
"special": true
|
55 |
+
}
|
56 |
+
],
|
57 |
+
"normalizer": {
|
58 |
+
"type": "BertNormalizer",
|
59 |
+
"clean_text": true,
|
60 |
+
"handle_chinese_chars": true,
|
61 |
+
"strip_accents": null,
|
62 |
+
"lowercase": true
|
63 |
+
},
|
64 |
+
"pre_tokenizer": {
|
65 |
+
"type": "BertPreTokenizer"
|
66 |
+
},
|
67 |
+
"post_processor": {
|
68 |
+
"type": "TemplateProcessing",
|
69 |
+
"single": [
|
70 |
+
{
|
71 |
+
"SpecialToken": {
|
72 |
+
"id": "[CLS]",
|
73 |
+
"type_id": 0
|
74 |
+
}
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"Sequence": {
|
78 |
+
"id": "A",
|
79 |
+
"type_id": 0
|
80 |
+
}
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"SpecialToken": {
|
84 |
+
"id": "[SEP]",
|
85 |
+
"type_id": 0
|
86 |
+
}
|
87 |
+
}
|
88 |
+
],
|
89 |
+
"pair": [
|
90 |
+
{
|
91 |
+
"SpecialToken": {
|
92 |
+
"id": "[CLS]",
|
93 |
+
"type_id": 0
|
94 |
+
}
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"Sequence": {
|
98 |
+
"id": "A",
|
99 |
+
"type_id": 0
|
100 |
+
}
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"SpecialToken": {
|
104 |
+
"id": "[SEP]",
|
105 |
+
"type_id": 0
|
106 |
+
}
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"Sequence": {
|
110 |
+
"id": "B",
|
111 |
+
"type_id": 1
|
112 |
+
}
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"SpecialToken": {
|
116 |
+
"id": "[SEP]",
|
117 |
+
"type_id": 1
|
118 |
+
}
|
119 |
+
}
|
120 |
+
],
|
121 |
+
"special_tokens": {
|
122 |
+
"[CLS]": {
|
123 |
+
"id": "[CLS]",
|
124 |
+
"ids": [
|
125 |
+
2
|
126 |
+
],
|
127 |
+
"tokens": [
|
128 |
+
"[CLS]"
|
129 |
+
]
|
130 |
+
},
|
131 |
+
"[SEP]": {
|
132 |
+
"id": "[SEP]",
|
133 |
+
"ids": [
|
134 |
+
3
|
135 |
+
],
|
136 |
+
"tokens": [
|
137 |
+
"[SEP]"
|
138 |
+
]
|
139 |
+
}
|
140 |
+
}
|
141 |
+
},
|
142 |
+
"decoder": {
|
143 |
+
"type": "WordPiece",
|
144 |
+
"prefix": "##",
|
145 |
+
"cleanup": true
|
146 |
+
},
|
147 |
+
"model": {
|
148 |
+
"type": "WordPiece",
|
149 |
+
"unk_token": "[UNK]",
|
150 |
+
"continuing_subword_prefix": "##",
|
151 |
+
"max_input_chars_per_word": 100,
|
152 |
+
"vocab": {
|
153 |
+
"[PAD]": 0,
|
154 |
+
"[UNK]": 1,
|
155 |
+
"[CLS]": 2,
|
156 |
+
"[SEP]": 3,
|
157 |
+
"[MASK]": 4,
|
158 |
+
"©": 5,
|
159 |
+
"،": 6,
|
160 |
+
"ء": 7,
|
161 |
+
"ا": 8,
|
162 |
+
"ب": 9,
|
163 |
+
"ت": 10,
|
164 |
+
"ث": 11,
|
165 |
+
"ج": 12,
|
166 |
+
"ح": 13,
|
167 |
+
"خ": 14,
|
168 |
+
"د": 15,
|
169 |
+
"ذ": 16,
|
170 |
+
"ر": 17,
|
171 |
+
"ز": 18,
|
172 |
+
"س": 19,
|
173 |
+
"ش": 20,
|
174 |
+
"ص": 21,
|
175 |
+
"ض": 22,
|
176 |
+
"ط": 23,
|
177 |
+
"ظ": 24,
|
178 |
+
"ع": 25,
|
179 |
+
"غ": 26,
|
180 |
+
"ف": 27,
|
181 |
+
"ق": 28,
|
182 |
+
"ل": 29,
|
183 |
+
"م": 30,
|
184 |
+
"ن": 31,
|
185 |
+
"ه": 32,
|
186 |
+
"و": 33,
|
187 |
+
"ي": 34,
|
188 |
+
"٪": 35,
|
189 |
+
"ټ": 36,
|
190 |
+
"پ": 37,
|
191 |
+
"ځ": 38,
|
192 |
+
"څ": 39,
|
193 |
+
"چ": 40,
|
194 |
+
"ډ": 41,
|
195 |
+
"ړ": 42,
|
196 |
+
"ږ": 43,
|
197 |
+
"ژ": 44,
|
198 |
+
"ښ": 45,
|
199 |
+
"ک": 46,
|
200 |
+
"ګ": 47,
|
201 |
+
"ں": 48,
|
202 |
+
"ڼ": 49,
|
203 |
+
"ی": 50,
|
204 |
+
"ۍ": 51,
|
205 |
+
"ې": 52,
|
206 |
+
"ے": 53,
|
207 |
+
"ە": 54,
|
208 |
+
"۰": 55,
|
209 |
+
"۱": 56,
|
210 |
+
"۲": 57,
|
211 |
+
"۳": 58,
|
212 |
+
"۴": 59,
|
213 |
+
"۵": 60,
|
214 |
+
"۶": 61,
|
215 |
+
"۷": 62,
|
216 |
+
"۸": 63,
|
217 |
+
"۹": 64,
|
218 |
+
"‼": 65,
|
219 |
+
"⁉": 66,
|
220 |
+
"↩": 67,
|
221 |
+
"↪": 68,
|
222 |
+
"⌨": 69,
|
223 |
+
"⏯": 70,
|
224 |
+
"⏰": 71,
|
225 |
+
"⏳": 72,
|
226 |
+
"ⓜ": 73,
|
227 |
+
"▫": 74,
|
228 |
+
"▶": 75,
|
229 |
+
"◻": 76,
|
230 |
+
"◽": 77,
|
231 |
+
"◾": 78,
|
232 |
+
"☀": 79,
|
233 |
+
"☁": 80,
|
234 |
+
"☃": 81,
|
235 |
+
"☎": 82,
|
236 |
+
"☑": 83,
|
237 |
+
"☔": 84,
|
238 |
+
"☕": 85,
|
239 |
+
"☘": 86,
|
240 |
+
"☝": 87,
|
241 |
+
"☠": 88,
|
242 |
+
"☢": 89,
|
243 |
+
"☣": 90,
|
244 |
+
"☹": 91,
|
245 |
+
"☺": 92,
|
246 |
+
"♀": 93,
|
247 |
+
"♂": 94,
|
248 |
+
"♠": 95,
|
249 |
+
"♣": 96,
|
250 |
+
"♥": 97,
|
251 |
+
"♦": 98,
|
252 |
+
"♨": 99,
|
253 |
+
"♻": 100,
|
254 |
+
"⚔": 101,
|
255 |
+
"⚕": 102,
|
256 |
+
"⚖": 103,
|
257 |
+
"⚛": 104,
|
258 |
+
"⚜": 105,
|
259 |
+
"⚠": 106,
|
260 |
+
"⚡": 107,
|
261 |
+
"⚪": 108,
|
262 |
+
"⚰": 109,
|
263 |
+
"⚾": 110,
|
264 |
+
"⛄": 111,
|
265 |
+
"⛈": 112,
|
266 |
+
"⛏": 113,
|
267 |
+
"⛓": 114,
|
268 |
+
"⛔": 115,
|
269 |
+
"⛰": 116,
|
270 |
+
"⛳": 117,
|
271 |
+
"⛷": 118,
|
272 |
+
"✂": 119,
|
273 |
+
"✅": 120,
|
274 |
+
"✈": 121,
|
275 |
+
"✊": 122,
|
276 |
+
"✋": 123,
|
277 |
+
"✌": 124,
|
278 |
+
"✍": 125,
|
279 |
+
"✏": 126,
|
280 |
+
"✒": 127,
|
281 |
+
"✔": 128,
|
282 |
+
"✖": 129,
|
283 |
+
"✨": 130,
|
284 |
+
"❄": 131,
|
285 |
+
"❌": 132,
|
286 |
+
"❎": 133,
|
287 |
+
"❓": 134,
|
288 |
+
"❕": 135,
|
289 |
+
"❗": 136,
|
290 |
+
"❣": 137,
|
291 |
+
"❤": 138,
|
292 |
+
"➖": 139,
|
293 |
+
"➰": 140,
|
294 |
+
"⤵": 141,
|
295 |
+
"⬅": 142,
|
296 |
+
"⬇": 143,
|
297 |
+
"⬛": 144,
|
298 |
+
"⭐": 145,
|
299 |
+
"⭕": 146,
|
300 |
+
"ﷺ": 147,
|
301 |
+
"ﷻ": 148,
|
302 |
+
"🀄": 149,
|
303 |
+
"🆔": 150,
|
304 |
+
"🌀": 151,
|
305 |
+
"🌃": 152,
|
306 |
+
"🌄": 153,
|
307 |
+
"🌅": 154,
|
308 |
+
"🌆": 155,
|
309 |
+
"🌈": 156,
|
310 |
+
"🌊": 157,
|
311 |
+
"🌌": 158,
|
312 |
+
"🌍": 159,
|
313 |
+
"🌎": 160,
|
314 |
+
"🌏": 161,
|
315 |
+
"🌐": 162,
|
316 |
+
"🌔": 163,
|
317 |
+
"🌕": 164,
|
318 |
+
"🌙": 165,
|
319 |
+
"🌚": 166,
|
320 |
+
"🌜": 167,
|
321 |
+
"🌝": 168,
|
322 |
+
"🌟": 169,
|
323 |
+
"🌤": 170,
|
324 |
+
"🌥": 171,
|
325 |
+
"🌦": 172,
|
326 |
+
"🌧": 173,
|
327 |
+
"🌨": 174,
|
328 |
+
"🌪": 175,
|
329 |
+
"🌫": 176,
|
330 |
+
"🌱": 177,
|
331 |
+
"🌲": 178,
|
332 |
+
"🌳": 179,
|
333 |
+
"🌴": 180,
|
334 |
+
"🌶": 181,
|
335 |
+
"🌷": 182,
|
336 |
+
"🌸": 183,
|
337 |
+
"🌹": 184,
|
338 |
+
"🌺": 185,
|
339 |
+
"🌻": 186,
|
340 |
+
"🌼": 187,
|
341 |
+
"🌾": 188,
|
342 |
+
"🌿": 189,
|
343 |
+
"🍀": 190,
|
344 |
+
"🍁": 191,
|
345 |
+
"🍂": 192,
|
346 |
+
"🍃": 193,
|
347 |
+
"🍆": 194,
|
348 |
+
"🍇": 195,
|
349 |
+
"🍋": 196,
|
350 |
+
"🍏": 197,
|
351 |
+
"🍑": 198,
|
352 |
+
"🍒": 199,
|
353 |
+
"🍖": 200,
|
354 |
+
"🍚": 201,
|
355 |
+
"🍛": 202,
|
356 |
+
"🍜": 203,
|
357 |
+
"🍥": 204,
|
358 |
+
"🍬": 205,
|
359 |
+
"🍶": 206,
|
360 |
+
"🍷": 207,
|
361 |
+
"🍸": 208,
|
362 |
+
"🍺": 209,
|
363 |
+
"🍻": 210,
|
364 |
+
"🍼": 211,
|
365 |
+
"🍾": 212,
|
366 |
+
"🎀": 213,
|
367 |
+
"🎁": 214,
|
368 |
+
"🎂": 215,
|
369 |
+
"🎃": 216,
|
370 |
+
"🎄": 217,
|
371 |
+
"🎅": 218,
|
372 |
+
"🎈": 219,
|
373 |
+
"🎉": 220,
|
374 |
+
"🎊": 221,
|
375 |
+
"🎋": 222,
|
376 |
+
"🎓": 223,
|
377 |
+
"🎗": 224,
|
378 |
+
"🎙": 225,
|
379 |
+
"🎞": 226,
|
380 |
+
"🎡": 227,
|
381 |
+
"🎤": 228,
|
382 |
+
"🎥": 229,
|
383 |
+
"🎧": 230,
|
384 |
+
"🎬": 231,
|
385 |
+
"🎭": 232,
|
386 |
+
"🎮": 233,
|
387 |
+
"🎯": 234,
|
388 |
+
"🎵": 235,
|
389 |
+
"🎶": 236,
|
390 |
+
"🎸": 237,
|
391 |
+
"🎼": 238,
|
392 |
+
"🏃": 239,
|
393 |
+
"🏅": 240,
|
394 |
+
"🏆": 241,
|
395 |
+
"🏍": 242,
|
396 |
+
"🏏": 243,
|
397 |
+
"🏔": 244,
|
398 |
+
"🏘": 245,
|
399 |
+
"🏝": 246,
|
400 |
+
"🏞": 247,
|
401 |
+
"🏟": 248,
|
402 |
+
"🏢": 249,
|
403 |
+
"🏥": 250,
|
404 |
+
"🏦": 251,
|
405 |
+
"🏧": 252,
|
406 |
+
"🏳": 253,
|
407 |
+
"🏴": 254,
|
408 |
+
"🏵": 255,
|
409 |
+
"🏹": 256,
|
410 |
+
"🏻": 257,
|
411 |
+
"🏼": 258,
|
412 |
+
"🏽": 259,
|
413 |
+
"🏾": 260,
|
414 |
+
"🏿": 261,
|
415 |
+
"🐃": 262,
|
416 |
+
"🐄": 263,
|
417 |
+
"🐅": 264,
|
418 |
+
"🐈": 265,
|
419 |
+
"🐊": 266,
|
420 |
+
"🐍": 267,
|
421 |
+
"🐎": 268,
|
422 |
+
"🐏": 269,
|
423 |
+
"🐐": 270,
|
424 |
+
"🐒": 271,
|
425 |
+
"🐓": 272,
|
426 |
+
"🐔": 273,
|
427 |
+
"🐕": 274,
|
428 |
+
"🐖": 275,
|
429 |
+
"🐗": 276,
|
430 |
+
"🐘": 277,
|
431 |
+
"🐜": 278,
|
432 |
+
"🐤": 279,
|
433 |
+
"🐦": 280,
|
434 |
+
"🐧": 281,
|
435 |
+
"🐩": 282,
|
436 |
+
"🐫": 283,
|
437 |
+
"🐱": 284,
|
438 |
+
"🐴": 285,
|
439 |
+
"🐶": 286,
|
440 |
+
"🐷": 287,
|
441 |
+
"🐺": 288,
|
442 |
+
"🐼": 289,
|
443 |
+
"👀": 290,
|
444 |
+
"👁": 291,
|
445 |
+
"👂": 292,
|
446 |
+
"👃": 293,
|
447 |
+
"👅": 294,
|
448 |
+
"👆": 295,
|
449 |
+
"👇": 296,
|
450 |
+
"👈": 297,
|
451 |
+
"👉": 298,
|
452 |
+
"👊": 299,
|
453 |
+
"👋": 300,
|
454 |
+
"👌": 301,
|
455 |
+
"👍": 302,
|
456 |
+
"👎": 303,
|
457 |
+
"👏": 304,
|
458 |
+
"👐": 305,
|
459 |
+
"👑": 306,
|
460 |
+
"👔": 307,
|
461 |
+
"👙": 308,
|
462 |
+
"👚": 309,
|
463 |
+
"👡": 310,
|
464 |
+
"👤": 311,
|
465 |
+
"👥": 312,
|
466 |
+
"👨": 313,
|
467 |
+
"👩": 314,
|
468 |
+
"👪": 315,
|
469 |
+
"👫": 316,
|
470 |
+
"👬": 317,
|
471 |
+
"👭": 318,
|
472 |
+
"👮": 319,
|
473 |
+
"👯": 320,
|
474 |
+
"👲": 321,
|
475 |
+
"👳": 322,
|
476 |
+
"👴": 323,
|
477 |
+
"👵": 324,
|
478 |
+
"👸": 325,
|
479 |
+
"👹": 326,
|
480 |
+
"👺": 327,
|
481 |
+
"👻": 328,
|
482 |
+
"👼": 329,
|
483 |
+
"👽": 330,
|
484 |
+
"👿": 331,
|
485 |
+
"💀": 332,
|
486 |
+
"💁": 333,
|
487 |
+
"💂": 334,
|
488 |
+
"💃": 335,
|
489 |
+
"💄": 336,
|
490 |
+
"💅": 337,
|
491 |
+
"💆": 338,
|
492 |
+
"💉": 339,
|
493 |
+
"💋": 340,
|
494 |
+
"💌": 341,
|
495 |
+
"💍": 342,
|
496 |
+
"💎": 343,
|
497 |
+
"💏": 344,
|
498 |
+
"💐": 345,
|
499 |
+
"💑": 346,
|
500 |
+
"💓": 347,
|
501 |
+
"💔": 348,
|
502 |
+
"💕": 349,
|
503 |
+
"💖": 350,
|
504 |
+
"💗": 351,
|
505 |
+
"💘": 352,
|
506 |
+
"💙": 353,
|
507 |
+
"💚": 354,
|
508 |
+
"💛": 355,
|
509 |
+
"💜": 356,
|
510 |
+
"💝": 357,
|
511 |
+
"💞": 358,
|
512 |
+
"💟": 359,
|
513 |
+
"💠": 360,
|
514 |
+
"💡": 361,
|
515 |
+
"💢": 362,
|
516 |
+
"💣": 363,
|
517 |
+
"💥": 364,
|
518 |
+
"💦": 365,
|
519 |
+
"💧": 366,
|
520 |
+
"💨": 367,
|
521 |
+
"💩": 368,
|
522 |
+
"💪": 369,
|
523 |
+
"💫": 370,
|
524 |
+
"💬": 371,
|
525 |
+
"💭": 372,
|
526 |
+
"💯": 373,
|
527 |
+
"💰": 374,
|
528 |
+
"💱": 375,
|
529 |
+
"💲": 376,
|
530 |
+
"💴": 377,
|
531 |
+
"💵": 378,
|
532 |
+
"💷": 379,
|
533 |
+
"💸": 380,
|
534 |
+
"💻": 381,
|
535 |
+
"💿": 382,
|
536 |
+
"📌": 383,
|
537 |
+
"📍": 384,
|
538 |
+
"📒": 385,
|
539 |
+
"📓": 386,
|
540 |
+
"📕": 387,
|
541 |
+
"📖": 388,
|
542 |
+
"📗": 389,
|
543 |
+
"📘": 390,
|
544 |
+
"📙": 391,
|
545 |
+
"📚": 392,
|
546 |
+
"📜": 393,
|
547 |
+
"📝": 394,
|
548 |
+
"📞": 395,
|
549 |
+
"📢": 396,
|
550 |
+
"📣": 397,
|
551 |
+
"📩": 398,
|
552 |
+
"📰": 399,
|
553 |
+
"📱": 400,
|
554 |
+
"📲": 401,
|
555 |
+
"📷": 402,
|
556 |
+
"📸": 403,
|
557 |
+
"📽": 404,
|
558 |
+
"📿": 405,
|
559 |
+
"🔁": 406,
|
560 |
+
"🔃": 407,
|
561 |
+
"🔄": 408,
|
562 |
+
"🔇": 409,
|
563 |
+
"🔉": 410,
|
564 |
+
"🔊": 411,
|
565 |
+
"🔎": 412,
|
566 |
+
"🔏": 413,
|
567 |
+
"🔐": 414,
|
568 |
+
"🔒": 415,
|
569 |
+
"🔓": 416,
|
570 |
+
"🔕": 417,
|
571 |
+
"🔗": 418,
|
572 |
+
"🔘": 419,
|
573 |
+
"🔙": 420,
|
574 |
+
"🔜": 421,
|
575 |
+
"🔝": 422,
|
576 |
+
"🔞": 423,
|
577 |
+
"🔥": 424,
|
578 |
+
"🔦": 425,
|
579 |
+
"🔧": 426,
|
580 |
+
"🔪": 427,
|
581 |
+
"🔫": 428,
|
582 |
+
"🔭": 429,
|
583 |
+
"🔮": 430,
|
584 |
+
"🔳": 431,
|
585 |
+
"🔴": 432,
|
586 |
+
"🔵": 433,
|
587 |
+
"🔶": 434,
|
588 |
+
"🔷": 435,
|
589 |
+
"🔸": 436,
|
590 |
+
"🔹": 437,
|
591 |
+
"🔺": 438,
|
592 |
+
"🔻": 439,
|
593 |
+
"🕊": 440,
|
594 |
+
"🕋": 441,
|
595 |
+
"🕌": 442,
|
596 |
+
"🕐": 443,
|
597 |
+
"🕒": 444,
|
598 |
+
"🕛": 445,
|
599 |
+
"🕯": 446,
|
600 |
+
"🕵": 447,
|
601 |
+
"🕶": 448,
|
602 |
+
"🕷": 449,
|
603 |
+
"🕸": 450,
|
604 |
+
"🖇": 451,
|
605 |
+
"🖊": 452,
|
606 |
+
"🖋": 453,
|
607 |
+
"🖌": 454,
|
608 |
+
"🖍": 455,
|
609 |
+
"🖐": 456,
|
610 |
+
"🖕": 457,
|
611 |
+
"🖤": 458,
|
612 |
+
"🖥": 459,
|
613 |
+
"🖨": 460,
|
614 |
+
"🗓": 461,
|
615 |
+
"🗡": 462,
|
616 |
+
"🗣": 463,
|
617 |
+
"🗳": 464,
|
618 |
+
"🗻": 465,
|
619 |
+
"😀": 466,
|
620 |
+
"😁": 467,
|
621 |
+
"😂": 468,
|
622 |
+
"😃": 469,
|
623 |
+
"😄": 470,
|
624 |
+
"😅": 471,
|
625 |
+
"😆": 472,
|
626 |
+
"😇": 473,
|
627 |
+
"😈": 474,
|
628 |
+
"😉": 475,
|
629 |
+
"😊": 476,
|
630 |
+
"😋": 477,
|
631 |
+
"😌": 478,
|
632 |
+
"😍": 479,
|
633 |
+
"😎": 480,
|
634 |
+
"😏": 481,
|
635 |
+
"😐": 482,
|
636 |
+
"😑": 483,
|
637 |
+
"😒": 484,
|
638 |
+
"😓": 485,
|
639 |
+
"😔": 486,
|
640 |
+
"😕": 487,
|
641 |
+
"😖": 488,
|
642 |
+
"😗": 489,
|
643 |
+
"😘": 490,
|
644 |
+
"😙": 491,
|
645 |
+
"😚": 492,
|
646 |
+
"😛": 493,
|
647 |
+
"😜": 494,
|
648 |
+
"😝": 495,
|
649 |
+
"😞": 496,
|
650 |
+
"😟": 497,
|
651 |
+
"😠": 498,
|
652 |
+
"😡": 499,
|
653 |
+
"😢": 500,
|
654 |
+
"😣": 501,
|
655 |
+
"😤": 502,
|
656 |
+
"😥": 503,
|
657 |
+
"😦": 504,
|
658 |
+
"😧": 505,
|
659 |
+
"😨": 506,
|
660 |
+
"😩": 507,
|
661 |
+
"😪": 508,
|
662 |
+
"😫": 509,
|
663 |
+
"😬": 510,
|
664 |
+
"😭": 511,
|
665 |
+
"😮": 512,
|
666 |
+
"😯": 513,
|
667 |
+
"😰": 514,
|
668 |
+
"😱": 515,
|
669 |
+
"😲": 516,
|
670 |
+
"😳": 517,
|
671 |
+
"😴": 518,
|
672 |
+
"😵": 519,
|
673 |
+
"😶": 520,
|
674 |
+
"😷": 521,
|
675 |
+
"😸": 522,
|
676 |
+
"😹": 523,
|
677 |
+
"😺": 524,
|
678 |
+
"😼": 525,
|
679 |
+
"😾": 526,
|
680 |
+
"🙁": 527,
|
681 |
+
"🙂": 528,
|
682 |
+
"🙃": 529,
|
683 |
+
"🙄": 530,
|
684 |
+
"🙅": 531,
|
685 |
+
"🙆": 532,
|
686 |
+
"🙇": 533,
|
687 |
+
"🙈": 534,
|
688 |
+
"🙉": 535,
|
689 |
+
"🙊": 536,
|
690 |
+
"🙋": 537,
|
691 |
+
"🙌": 538,
|
692 |
+
"🙍": 539,
|
693 |
+
"🙎": 540,
|
694 |
+
"🙏": 541,
|
695 |
+
"🚁": 542,
|
696 |
+
"🚌": 543,
|
697 |
+
"🚎": 544,
|
698 |
+
"🚑": 545,
|
699 |
+
"🚓": 546,
|
700 |
+
"🚘": 547,
|
701 |
+
"🚨": 548,
|
702 |
+
"🚩": 549,
|
703 |
+
"🚪": 550,
|
704 |
+
"🚬": 551,
|
705 |
+
"🚮": 552,
|
706 |
+
"🚶": 553,
|
707 |
+
"🚷": 554,
|
708 |
+
"🚸": 555,
|
709 |
+
"🚿": 556,
|
710 |
+
"🛀": 557,
|
711 |
+
"🛁": 558,
|
712 |
+
"🛅": 559,
|
713 |
+
"🛌": 560,
|
714 |
+
"🛑": 561,
|
715 |
+
"🛠": 562,
|
716 |
+
"🛡": 563,
|
717 |
+
"🛣": 564,
|
718 |
+
"🛫": 565,
|
719 |
+
"🟢": 566,
|
720 |
+
"🟥": 567,
|
721 |
+
"🟩": 568,
|
722 |
+
"🤌": 569,
|
723 |
+
"🤍": 570,
|
724 |
+
"🤎": 571,
|
725 |
+
"🤏": 572,
|
726 |
+
"🤐": 573,
|
727 |
+
"🤑": 574,
|
728 |
+
"🤒": 575,
|
729 |
+
"🤓": 576,
|
730 |
+
"🤔": 577,
|
731 |
+
"🤕": 578,
|
732 |
+
"🤗": 579,
|
733 |
+
"🤘": 580,
|
734 |
+
"🤙": 581,
|
735 |
+
"🤚": 582,
|
736 |
+
"🤛": 583,
|
737 |
+
"🤜": 584,
|
738 |
+
"🤝": 585,
|
739 |
+
"🤞": 586,
|
740 |
+
"🤟": 587,
|
741 |
+
"🤠": 588,
|
742 |
+
"🤡": 589,
|
743 |
+
"🤢": 590,
|
744 |
+
"🤣": 591,
|
745 |
+
"🤤": 592,
|
746 |
+
"🤥": 593,
|
747 |
+
"🤦": 594,
|
748 |
+
"🤧": 595,
|
749 |
+
"🤨": 596,
|
750 |
+
"🤩": 597,
|
751 |
+
"🤪": 598,
|
752 |
+
"🤫": 599,
|
753 |
+
"🤬": 600,
|
754 |
+
"🤭": 601,
|
755 |
+
"🤮": 602,
|
756 |
+
"🤯": 603,
|
757 |
+
"🤲": 604,
|
758 |
+
"🤳": 605,
|
759 |
+
"🤷": 606,
|
760 |
+
"🤸": 607,
|
761 |
+
"🤺": 608,
|
762 |
+
"🥀": 609,
|
763 |
+
"🥂": 610,
|
764 |
+
"🥄": 611,
|
765 |
+
"🥒": 612,
|
766 |
+
"🥕": 613,
|
767 |
+
"🥗": 614,
|
768 |
+
"🥛": 615,
|
769 |
+
"🥝": 616,
|
770 |
+
"🥞": 617,
|
771 |
+
"🥤": 618,
|
772 |
+
"🥦": 619,
|
773 |
+
"🥪": 620,
|
774 |
+
"🥬": 621,
|
775 |
+
"🥰": 622,
|
776 |
+
"🥱": 623,
|
777 |
+
"🥲": 624,
|
778 |
+
"🥳": 625,
|
779 |
+
"🥴": 626,
|
780 |
+
"🥵": 627,
|
781 |
+
"🥶": 628,
|
782 |
+
"🥷": 629,
|
783 |
+
"🥸": 630,
|
784 |
+
"🥹": 631,
|
785 |
+
"🥺": 632,
|
786 |
+
"🦁": 633,
|
787 |
+
"🦄": 634,
|
788 |
+
"🦅": 635,
|
789 |
+
"🦇": 636,
|
790 |
+
"🦋": 637,
|
791 |
+
"🦌": 638,
|
792 |
+
"🦓": 639,
|
793 |
+
"🦔": 640,
|
794 |
+
"🦘": 641,
|
795 |
+
"🦙": 642,
|
796 |
+
"🦜": 643,
|
797 |
+
"🦟": 644,
|
798 |
+
"🦢": 645,
|
799 |
+
"🦤": 646,
|
800 |
+
"🦥": 647,
|
801 |
+
"🦩": 648,
|
802 |
+
"🦮": 649,
|
803 |
+
"🦴": 650,
|
804 |
+
"🦵": 651,
|
805 |
+
"🦶": 652,
|
806 |
+
"🦹": 653,
|
807 |
+
"🦺": 654,
|
808 |
+
"🦻": 655,
|
809 |
+
"🦾": 656,
|
810 |
+
"🧏": 657,
|
811 |
+
"🧐": 658,
|
812 |
+
"🧑": 659,
|
813 |
+
"🧕": 660,
|
814 |
+
"🧚": 661,
|
815 |
+
"🧛": 662,
|
816 |
+
"🧠": 663,
|
817 |
+
"🧡": 664,
|
818 |
+
"🧣": 665,
|
819 |
+
"🧬": 666,
|
820 |
+
"🧵": 667,
|
821 |
+
"🧸": 668,
|
822 |
+
"🧹": 669,
|
823 |
+
"🧾": 670,
|
824 |
+
"🧿": 671,
|
825 |
+
"🩶": 672,
|
826 |
+
"🩸": 673,
|
827 |
+
"🩹": 674,
|
828 |
+
"🪀": 675,
|
829 |
+
"🪕": 676,
|
830 |
+
"🪙": 677,
|
831 |
+
"🪠": 678,
|
832 |
+
"🪦": 679,
|
833 |
+
"🪴": 680,
|
834 |
+
"🪷": 681,
|
835 |
+
"🫀": 682,
|
836 |
+
"🫂": 683,
|
837 |
+
"🫏": 684,
|
838 |
+
"🫐": 685,
|
839 |
+
"🫓": 686,
|
840 |
+
"🫘": 687,
|
841 |
+
"🫠": 688,
|
842 |
+
"🫡": 689,
|
843 |
+
"🫢": 690,
|
844 |
+
"🫣": 691,
|
845 |
+
"🫤": 692,
|
846 |
+
"🫥": 693,
|
847 |
+
"🫧": 694,
|
848 |
+
"🫨": 695,
|
849 |
+
"🫰": 696,
|
850 |
+
"🫱": 697,
|
851 |
+
"🫲": 698,
|
852 |
+
"🫳": 699,
|
853 |
+
"🫴": 700,
|
854 |
+
"🫵": 701,
|
855 |
+
"🫶": 702
|
856 |
+
}
|
857 |
+
}
|
858 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_lower_case": true,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"model_max_length": 512,
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"sep_token": "[SEP]",
|
9 |
+
"strip_accents": null,
|
10 |
+
"tokenize_chinese_chars": true,
|
11 |
+
"tokenizer_class": "BertTokenizer",
|
12 |
+
"unk_token": "[UNK]"
|
13 |
+
}
|
vocab.txt
ADDED
@@ -0,0 +1,703 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[PAD]
|
2 |
+
[UNK]
|
3 |
+
[CLS]
|
4 |
+
[SEP]
|
5 |
+
[MASK]
|
6 |
+
©
|
7 |
+
،
|
8 |
+
ء
|
9 |
+
ا
|
10 |
+
ب
|
11 |
+
ت
|
12 |
+
ث
|
13 |
+
ج
|
14 |
+
ح
|
15 |
+
خ
|
16 |
+
د
|
17 |
+
ذ
|
18 |
+
ر
|
19 |
+
ز
|
20 |
+
س
|
21 |
+
ش
|
22 |
+
ص
|
23 |
+
ض
|
24 |
+
ط
|
25 |
+
ظ
|
26 |
+
ع
|
27 |
+
غ
|
28 |
+
ف
|
29 |
+
ق
|
30 |
+
ل
|
31 |
+
م
|
32 |
+
ن
|
33 |
+
ه
|
34 |
+
و
|
35 |
+
ي
|
36 |
+
٪
|
37 |
+
ټ
|
38 |
+
پ
|
39 |
+
ځ
|
40 |
+
څ
|
41 |
+
چ
|
42 |
+
ډ
|
43 |
+
ړ
|
44 |
+
ږ
|
45 |
+
ژ
|
46 |
+
ښ
|
47 |
+
ک
|
48 |
+
ګ
|
49 |
+
ں
|
50 |
+
ڼ
|
51 |
+
ی
|
52 |
+
ۍ
|
53 |
+
ې
|
54 |
+
ے
|
55 |
+
ە
|
56 |
+
۰
|
57 |
+
۱
|
58 |
+
۲
|
59 |
+
۳
|
60 |
+
۴
|
61 |
+
۵
|
62 |
+
۶
|
63 |
+
۷
|
64 |
+
۸
|
65 |
+
۹
|
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 |
+
✋
|
125 |
+
✌
|
126 |
+
✍
|
127 |
+
✏
|
128 |
+
✒
|
129 |
+
✔
|
130 |
+
✖
|
131 |
+
✨
|
132 |
+
❄
|
133 |
+
❌
|
134 |
+
❎
|
135 |
+
❓
|
136 |
+
❕
|
137 |
+
❗
|
138 |
+
❣
|
139 |
+
❤
|
140 |
+
➖
|
141 |
+
➰
|
142 |
+
⤵
|
143 |
+
⬅
|
144 |
+
⬇
|
145 |
+
⬛
|
146 |
+
⭐
|
147 |
+
⭕
|
148 |
+
ﷺ
|
149 |
+
ﷻ
|
150 |
+
🀄
|
151 |
+
🆔
|
152 |
+
🌀
|
153 |
+
🌃
|
154 |
+
🌄
|
155 |
+
🌅
|
156 |
+
🌆
|
157 |
+
🌈
|
158 |
+
🌊
|
159 |
+
🌌
|
160 |
+
🌍
|
161 |
+
🌎
|
162 |
+
🌏
|
163 |
+
🌐
|
164 |
+
🌔
|
165 |
+
🌕
|
166 |
+
🌙
|
167 |
+
🌚
|
168 |
+
🌜
|
169 |
+
🌝
|
170 |
+
🌟
|
171 |
+
🌤
|
172 |
+
🌥
|
173 |
+
🌦
|
174 |
+
🌧
|
175 |
+
🌨
|
176 |
+
🌪
|
177 |
+
🌫
|
178 |
+
🌱
|
179 |
+
🌲
|
180 |
+
🌳
|
181 |
+
🌴
|
182 |
+
🌶
|
183 |
+
🌷
|
184 |
+
🌸
|
185 |
+
🌹
|
186 |
+
🌺
|
187 |
+
🌻
|
188 |
+
🌼
|
189 |
+
🌾
|
190 |
+
🌿
|
191 |
+
🍀
|
192 |
+
🍁
|
193 |
+
🍂
|
194 |
+
🍃
|
195 |
+
🍆
|
196 |
+
🍇
|
197 |
+
🍋
|
198 |
+
🍏
|
199 |
+
🍑
|
200 |
+
🍒
|
201 |
+
🍖
|
202 |
+
🍚
|
203 |
+
🍛
|
204 |
+
🍜
|
205 |
+
🍥
|
206 |
+
🍬
|
207 |
+
🍶
|
208 |
+
🍷
|
209 |
+
🍸
|
210 |
+
🍺
|
211 |
+
🍻
|
212 |
+
🍼
|
213 |
+
🍾
|
214 |
+
🎀
|
215 |
+
🎁
|
216 |
+
🎂
|
217 |
+
🎃
|
218 |
+
🎄
|
219 |
+
🎅
|
220 |
+
🎈
|
221 |
+
🎉
|
222 |
+
🎊
|
223 |
+
🎋
|
224 |
+
🎓
|
225 |
+
🎗
|
226 |
+
🎙
|
227 |
+
🎞
|
228 |
+
🎡
|
229 |
+
🎤
|
230 |
+
🎥
|
231 |
+
🎧
|
232 |
+
🎬
|
233 |
+
🎭
|
234 |
+
🎮
|
235 |
+
🎯
|
236 |
+
🎵
|
237 |
+
🎶
|
238 |
+
🎸
|
239 |
+
🎼
|
240 |
+
🏃
|
241 |
+
🏅
|
242 |
+
🏆
|
243 |
+
🏍
|
244 |
+
🏏
|
245 |
+
🏔
|
246 |
+
🏘
|
247 |
+
🏝
|
248 |
+
🏞
|
249 |
+
🏟
|
250 |
+
🏢
|
251 |
+
🏥
|
252 |
+
🏦
|
253 |
+
🏧
|
254 |
+
🏳
|
255 |
+
🏴
|
256 |
+
🏵
|
257 |
+
🏹
|
258 |
+
🏻
|
259 |
+
🏼
|
260 |
+
🏽
|
261 |
+
🏾
|
262 |
+
🏿
|
263 |
+
🐃
|
264 |
+
🐄
|
265 |
+
🐅
|
266 |
+
🐈
|
267 |
+
🐊
|
268 |
+
🐍
|
269 |
+
🐎
|
270 |
+
🐏
|
271 |
+
🐐
|
272 |
+
🐒
|
273 |
+
🐓
|
274 |
+
🐔
|
275 |
+
🐕
|
276 |
+
🐖
|
277 |
+
🐗
|
278 |
+
🐘
|
279 |
+
🐜
|
280 |
+
🐤
|
281 |
+
🐦
|
282 |
+
🐧
|
283 |
+
🐩
|
284 |
+
🐫
|
285 |
+
🐱
|
286 |
+
🐴
|
287 |
+
🐶
|
288 |
+
🐷
|
289 |
+
🐺
|
290 |
+
🐼
|
291 |
+
👀
|
292 |
+
👁
|
293 |
+
👂
|
294 |
+
👃
|
295 |
+
👅
|
296 |
+
👆
|
297 |
+
👇
|
298 |
+
👈
|
299 |
+
👉
|
300 |
+
👊
|
301 |
+
👋
|
302 |
+
👌
|
303 |
+
👍
|
304 |
+
👎
|
305 |
+
👏
|
306 |
+
👐
|
307 |
+
👑
|
308 |
+
👔
|
309 |
+
👙
|
310 |
+
👚
|
311 |
+
👡
|
312 |
+
👤
|
313 |
+
👥
|
314 |
+
👨
|
315 |
+
👩
|
316 |
+
👪
|
317 |
+
👫
|
318 |
+
👬
|
319 |
+
👭
|
320 |
+
👮
|
321 |
+
👯
|
322 |
+
👲
|
323 |
+
👳
|
324 |
+
👴
|
325 |
+
👵
|
326 |
+
👸
|
327 |
+
👹
|
328 |
+
👺
|
329 |
+
👻
|
330 |
+
👼
|
331 |
+
👽
|
332 |
+
👿
|
333 |
+
💀
|
334 |
+
💁
|
335 |
+
💂
|
336 |
+
💃
|
337 |
+
💄
|
338 |
+
💅
|
339 |
+
💆
|
340 |
+
💉
|
341 |
+
💋
|
342 |
+
💌
|
343 |
+
💍
|
344 |
+
💎
|
345 |
+
💏
|
346 |
+
💐
|
347 |
+
💑
|
348 |
+
💓
|
349 |
+
💔
|
350 |
+
💕
|
351 |
+
💖
|
352 |
+
💗
|
353 |
+
💘
|
354 |
+
💙
|
355 |
+
💚
|
356 |
+
💛
|
357 |
+
💜
|
358 |
+
💝
|
359 |
+
💞
|
360 |
+
💟
|
361 |
+
💠
|
362 |
+
💡
|
363 |
+
💢
|
364 |
+
💣
|
365 |
+
💥
|
366 |
+
💦
|
367 |
+
💧
|
368 |
+
💨
|
369 |
+
💩
|
370 |
+
💪
|
371 |
+
💫
|
372 |
+
💬
|
373 |
+
💭
|
374 |
+
💯
|
375 |
+
💰
|
376 |
+
💱
|
377 |
+
💲
|
378 |
+
💴
|
379 |
+
💵
|
380 |
+
💷
|
381 |
+
💸
|
382 |
+
💻
|
383 |
+
💿
|
384 |
+
📌
|
385 |
+
📍
|
386 |
+
📒
|
387 |
+
📓
|
388 |
+
📕
|
389 |
+
📖
|
390 |
+
📗
|
391 |
+
📘
|
392 |
+
📙
|
393 |
+
📚
|
394 |
+
📜
|
395 |
+
📝
|
396 |
+
📞
|
397 |
+
📢
|
398 |
+
📣
|
399 |
+
📩
|
400 |
+
📰
|
401 |
+
📱
|
402 |
+
📲
|
403 |
+
📷
|
404 |
+
📸
|
405 |
+
📽
|
406 |
+
📿
|
407 |
+
🔁
|
408 |
+
🔃
|
409 |
+
🔄
|
410 |
+
🔇
|
411 |
+
🔉
|
412 |
+
🔊
|
413 |
+
🔎
|
414 |
+
🔏
|
415 |
+
🔐
|
416 |
+
🔒
|
417 |
+
🔓
|
418 |
+
🔕
|
419 |
+
🔗
|
420 |
+
🔘
|
421 |
+
🔙
|
422 |
+
🔜
|
423 |
+
🔝
|
424 |
+
🔞
|
425 |
+
🔥
|
426 |
+
🔦
|
427 |
+
🔧
|
428 |
+
🔪
|
429 |
+
🔫
|
430 |
+
🔭
|
431 |
+
🔮
|
432 |
+
🔳
|
433 |
+
🔴
|
434 |
+
🔵
|
435 |
+
🔶
|
436 |
+
🔷
|
437 |
+
🔸
|
438 |
+
🔹
|
439 |
+
🔺
|
440 |
+
🔻
|
441 |
+
🕊
|
442 |
+
🕋
|
443 |
+
🕌
|
444 |
+
🕐
|
445 |
+
🕒
|
446 |
+
🕛
|
447 |
+
🕯
|
448 |
+
🕵
|
449 |
+
🕶
|
450 |
+
🕷
|
451 |
+
🕸
|
452 |
+
🖇
|
453 |
+
🖊
|
454 |
+
🖋
|
455 |
+
🖌
|
456 |
+
🖍
|
457 |
+
🖐
|
458 |
+
🖕
|
459 |
+
🖤
|
460 |
+
🖥
|
461 |
+
🖨
|
462 |
+
🗓
|
463 |
+
🗡
|
464 |
+
🗣
|
465 |
+
🗳
|
466 |
+
🗻
|
467 |
+
😀
|
468 |
+
😁
|
469 |
+
😂
|
470 |
+
😃
|
471 |
+
😄
|
472 |
+
😅
|
473 |
+
😆
|
474 |
+
😇
|
475 |
+
😈
|
476 |
+
😉
|
477 |
+
😊
|
478 |
+
😋
|
479 |
+
😌
|
480 |
+
😍
|
481 |
+
😎
|
482 |
+
😏
|
483 |
+
😐
|
484 |
+
😑
|
485 |
+
😒
|
486 |
+
😓
|
487 |
+
😔
|
488 |
+
😕
|
489 |
+
😖
|
490 |
+
😗
|
491 |
+
😘
|
492 |
+
😙
|
493 |
+
😚
|
494 |
+
😛
|
495 |
+
😜
|
496 |
+
😝
|
497 |
+
😞
|
498 |
+
😟
|
499 |
+
😠
|
500 |
+
😡
|
501 |
+
😢
|
502 |
+
😣
|
503 |
+
😤
|
504 |
+
😥
|
505 |
+
😦
|
506 |
+
😧
|
507 |
+
😨
|
508 |
+
😩
|
509 |
+
😪
|
510 |
+
😫
|
511 |
+
😬
|
512 |
+
😭
|
513 |
+
😮
|
514 |
+
😯
|
515 |
+
😰
|
516 |
+
😱
|
517 |
+
😲
|
518 |
+
😳
|
519 |
+
😴
|
520 |
+
😵
|
521 |
+
😶
|
522 |
+
😷
|
523 |
+
😸
|
524 |
+
😹
|
525 |
+
😺
|
526 |
+
😼
|
527 |
+
😾
|
528 |
+
🙁
|
529 |
+
🙂
|
530 |
+
🙃
|
531 |
+
🙄
|
532 |
+
🙅
|
533 |
+
🙆
|
534 |
+
🙇
|
535 |
+
🙈
|
536 |
+
🙉
|
537 |
+
🙊
|
538 |
+
🙋
|
539 |
+
🙌
|
540 |
+
🙍
|
541 |
+
🙎
|
542 |
+
🙏
|
543 |
+
🚁
|
544 |
+
🚌
|
545 |
+
🚎
|
546 |
+
🚑
|
547 |
+
🚓
|
548 |
+
🚘
|
549 |
+
🚨
|
550 |
+
🚩
|
551 |
+
🚪
|
552 |
+
🚬
|
553 |
+
🚮
|
554 |
+
🚶
|
555 |
+
🚷
|
556 |
+
🚸
|
557 |
+
🚿
|
558 |
+
🛀
|
559 |
+
🛁
|
560 |
+
🛅
|
561 |
+
🛌
|
562 |
+
🛑
|
563 |
+
🛠
|
564 |
+
🛡
|
565 |
+
🛣
|
566 |
+
🛫
|
567 |
+
🟢
|
568 |
+
🟥
|
569 |
+
🟩
|
570 |
+
🤌
|
571 |
+
🤍
|
572 |
+
🤎
|
573 |
+
🤏
|
574 |
+
🤐
|
575 |
+
🤑
|
576 |
+
🤒
|
577 |
+
🤓
|
578 |
+
🤔
|
579 |
+
🤕
|
580 |
+
🤗
|
581 |
+
🤘
|
582 |
+
🤙
|
583 |
+
🤚
|
584 |
+
🤛
|
585 |
+
🤜
|
586 |
+
🤝
|
587 |
+
🤞
|
588 |
+
🤟
|
589 |
+
🤠
|
590 |
+
🤡
|
591 |
+
🤢
|
592 |
+
🤣
|
593 |
+
🤤
|
594 |
+
🤥
|
595 |
+
🤦
|
596 |
+
🤧
|
597 |
+
🤨
|
598 |
+
🤩
|
599 |
+
🤪
|
600 |
+
🤫
|
601 |
+
🤬
|
602 |
+
🤭
|
603 |
+
🤮
|
604 |
+
🤯
|
605 |
+
🤲
|
606 |
+
🤳
|
607 |
+
🤷
|
608 |
+
🤸
|
609 |
+
🤺
|
610 |
+
🥀
|
611 |
+
🥂
|
612 |
+
🥄
|
613 |
+
🥒
|
614 |
+
🥕
|
615 |
+
🥗
|
616 |
+
🥛
|
617 |
+
🥝
|
618 |
+
🥞
|
619 |
+
🥤
|
620 |
+
🥦
|
621 |
+
🥪
|
622 |
+
🥬
|
623 |
+
🥰
|
624 |
+
🥱
|
625 |
+
🥲
|
626 |
+
🥳
|
627 |
+
🥴
|
628 |
+
🥵
|
629 |
+
🥶
|
630 |
+
🥷
|
631 |
+
🥸
|
632 |
+
🥹
|
633 |
+
🥺
|
634 |
+
🦁
|
635 |
+
🦄
|
636 |
+
🦅
|
637 |
+
🦇
|
638 |
+
🦋
|
639 |
+
🦌
|
640 |
+
🦓
|
641 |
+
🦔
|
642 |
+
🦘
|
643 |
+
🦙
|
644 |
+
🦜
|
645 |
+
🦟
|
646 |
+
🦢
|
647 |
+
🦤
|
648 |
+
🦥
|
649 |
+
🦩
|
650 |
+
🦮
|
651 |
+
🦴
|
652 |
+
🦵
|
653 |
+
🦶
|
654 |
+
🦹
|
655 |
+
🦺
|
656 |
+
🦻
|
657 |
+
🦾
|
658 |
+
🧏
|
659 |
+
🧐
|
660 |
+
🧑
|
661 |
+
🧕
|
662 |
+
🧚
|
663 |
+
🧛
|
664 |
+
🧠
|
665 |
+
🧡
|
666 |
+
🧣
|
667 |
+
🧬
|
668 |
+
🧵
|
669 |
+
🧸
|
670 |
+
🧹
|
671 |
+
🧾
|
672 |
+
🧿
|
673 |
+
🩶
|
674 |
+
🩸
|
675 |
+
🩹
|
676 |
+
🪀
|
677 |
+
🪕
|
678 |
+
🪙
|
679 |
+
🪠
|
680 |
+
🪦
|
681 |
+
🪴
|
682 |
+
🪷
|
683 |
+
🫀
|
684 |
+
🫂
|
685 |
+
🫏
|
686 |
+
🫐
|
687 |
+
🫓
|
688 |
+
🫘
|
689 |
+
🫠
|
690 |
+
🫡
|
691 |
+
🫢
|
692 |
+
🫣
|
693 |
+
🫤
|
694 |
+
🫥
|
695 |
+
🫧
|
696 |
+
🫨
|
697 |
+
🫰
|
698 |
+
🫱
|
699 |
+
🫲
|
700 |
+
🫳
|
701 |
+
🫴
|
702 |
+
🫵
|
703 |
+
🫶
|