indiejoseph
commited on
Commit
•
d77f180
1
Parent(s):
da8e80a
Training in progress, step 500
Browse files- added_tokens.json +184 -0
- config.json +75 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1524 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,184 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"㑃": 51365,
|
3 |
+
"㑭": 51411,
|
4 |
+
"㑰": 51393,
|
5 |
+
"㓋": 51428,
|
6 |
+
"㓟": 51405,
|
7 |
+
"㓽": 51430,
|
8 |
+
"㔁": 51402,
|
9 |
+
"㔷": 51288,
|
10 |
+
"㕃": 51424,
|
11 |
+
"㕇": 51346,
|
12 |
+
"㕍": 51336,
|
13 |
+
"㕷": 51331,
|
14 |
+
"㖥": 51316,
|
15 |
+
"㖭": 51271,
|
16 |
+
"㗇": 51280,
|
17 |
+
"㗋": 51325,
|
18 |
+
"㗱": 51289,
|
19 |
+
"㗳": 51440,
|
20 |
+
"㗻": 51420,
|
21 |
+
"㗾": 51291,
|
22 |
+
"㘉": 51284,
|
23 |
+
"㙒": 51389,
|
24 |
+
"㚲": 51416,
|
25 |
+
"㛱": 51334,
|
26 |
+
"㛻": 51406,
|
27 |
+
"㝙": 51382,
|
28 |
+
"㝫": 51376,
|
29 |
+
"㝿": 51338,
|
30 |
+
"㞓": 51299,
|
31 |
+
"㞜": 51417,
|
32 |
+
"㢌": 51279,
|
33 |
+
"㢜": 51359,
|
34 |
+
"㢸": 51435,
|
35 |
+
"㣒": 51295,
|
36 |
+
"㣜": 51438,
|
37 |
+
"㤓": 51401,
|
38 |
+
"㤟": 51390,
|
39 |
+
"㤳": 51394,
|
40 |
+
"㥶": 51388,
|
41 |
+
"㦨": 51341,
|
42 |
+
"㧜": 51292,
|
43 |
+
"㧧": 51332,
|
44 |
+
"㧵": 51448,
|
45 |
+
"㨂": 51273,
|
46 |
+
"㨘": 51342,
|
47 |
+
"㨾": 51364,
|
48 |
+
"㩕": 51326,
|
49 |
+
"㩙": 51443,
|
50 |
+
"㩻": 51353,
|
51 |
+
"㪹": 51404,
|
52 |
+
"㫗": 51330,
|
53 |
+
"㬢": 51398,
|
54 |
+
"㬮": 51310,
|
55 |
+
"㭂": 51383,
|
56 |
+
"㭋": 51410,
|
57 |
+
"㭛": 51361,
|
58 |
+
"㭬": 51392,
|
59 |
+
"㭾": 51290,
|
60 |
+
"㮇": 51363,
|
61 |
+
"㯰": 51327,
|
62 |
+
"㰮": 51335,
|
63 |
+
"㰸": 51297,
|
64 |
+
"㰹": 51387,
|
65 |
+
"㱒": 51339,
|
66 |
+
"㱱": 51366,
|
67 |
+
"㲈": 51351,
|
68 |
+
"㲻": 51385,
|
69 |
+
"㳮": 51315,
|
70 |
+
"㴝": 51275,
|
71 |
+
"㴫": 51293,
|
72 |
+
"㵕": 51378,
|
73 |
+
"㵖": 51303,
|
74 |
+
"㵞": 51377,
|
75 |
+
"㵻": 51403,
|
76 |
+
"㶦": 51357,
|
77 |
+
"㶺": 51328,
|
78 |
+
"㸀": 51414,
|
79 |
+
"㸛": 51352,
|
80 |
+
"㹒": 51370,
|
81 |
+
"㹵": 51319,
|
82 |
+
"㹾": 51374,
|
83 |
+
"㽂": 51431,
|
84 |
+
"㽇": 51277,
|
85 |
+
"㾓": 51441,
|
86 |
+
"㾘": 51447,
|
87 |
+
"㾝": 51323,
|
88 |
+
"㿺": 51437,
|
89 |
+
"䀆": 51368,
|
90 |
+
"䀨": 51412,
|
91 |
+
"䀳": 51309,
|
92 |
+
"䁓": 51384,
|
93 |
+
"䁪": 51274,
|
94 |
+
"䁵": 51371,
|
95 |
+
"䁷": 51380,
|
96 |
+
"䂾": 51445,
|
97 |
+
"䃛": 51452,
|
98 |
+
"䄒": 51396,
|
99 |
+
"䄛": 51287,
|
100 |
+
"䄪": 51409,
|
101 |
+
"䄮": 51313,
|
102 |
+
"䅤": 51436,
|
103 |
+
"䆭": 51344,
|
104 |
+
"䈟": 51415,
|
105 |
+
"䈢": 51399,
|
106 |
+
"䉔": 51444,
|
107 |
+
"䉪": 51281,
|
108 |
+
"䉵": 51407,
|
109 |
+
"䊦": 51272,
|
110 |
+
"䊯": 51386,
|
111 |
+
"䊵": 51369,
|
112 |
+
"䋒": 51305,
|
113 |
+
"䌟": 51362,
|
114 |
+
"䏙": 51400,
|
115 |
+
"䏺": 51358,
|
116 |
+
"䐔": 51306,
|
117 |
+
"䐥": 51282,
|
118 |
+
"䑛": 51276,
|
119 |
+
"䒭": 51354,
|
120 |
+
"䕊": 51298,
|
121 |
+
"䕱": 51419,
|
122 |
+
"䕼": 51311,
|
123 |
+
"䘀": 51296,
|
124 |
+
"䘆": 51283,
|
125 |
+
"䘳": 51321,
|
126 |
+
"䚔": 51300,
|
127 |
+
"䚗": 51285,
|
128 |
+
"䛮": 51308,
|
129 |
+
"䛷": 51322,
|
130 |
+
"䝟": 51432,
|
131 |
+
"䞟": 51329,
|
132 |
+
"䞨": 51372,
|
133 |
+
"䞾": 51343,
|
134 |
+
"䟕": 51278,
|
135 |
+
"䠊": 51427,
|
136 |
+
"䠮": 51314,
|
137 |
+
"䣸": 51375,
|
138 |
+
"䤄": 51333,
|
139 |
+
"䥚": 51449,
|
140 |
+
"䦞": 51349,
|
141 |
+
"䦥": 51391,
|
142 |
+
"䧐": 51433,
|
143 |
+
"䧬": 51451,
|
144 |
+
"䩐": 51360,
|
145 |
+
"䩢": 51421,
|
146 |
+
"䪐": 51423,
|
147 |
+
"䭃": 51345,
|
148 |
+
"䭋": 51355,
|
149 |
+
"䭡": 51302,
|
150 |
+
"䭮": 51320,
|
151 |
+
"䭽": 51324,
|
152 |
+
"䮺": 51439,
|
153 |
+
"䯡": 51379,
|
154 |
+
"䯧": 51350,
|
155 |
+
"䰝": 51425,
|
156 |
+
"䰢": 51348,
|
157 |
+
"䰣": 51367,
|
158 |
+
"䰺": 51397,
|
159 |
+
"䱏": 51312,
|
160 |
+
"䱰": 51356,
|
161 |
+
"䲒": 51294,
|
162 |
+
"䵎": 51395,
|
163 |
+
"䵜": 51408,
|
164 |
+
"䵦": 51450,
|
165 |
+
"䵯": 51304,
|
166 |
+
"䶡": 51426,
|
167 |
+
"䶵": 51337,
|
168 |
+
"嘺": 51413,
|
169 |
+
"嚝": 51442,
|
170 |
+
"攳": 51318,
|
171 |
+
"籅": 51317,
|
172 |
+
"藀": 51381,
|
173 |
+
"藬": 51418,
|
174 |
+
"蠾": 51301,
|
175 |
+
"譈": 51307,
|
176 |
+
"贉": 51446,
|
177 |
+
"躷": 51429,
|
178 |
+
"邭": 51434,
|
179 |
+
"鞝": 51340,
|
180 |
+
"饇": 51373,
|
181 |
+
"騇": 51347,
|
182 |
+
"鰦": 51286,
|
183 |
+
"齴": 51422
|
184 |
+
}
|
config.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "indiejoseph/bart-base-cantonese",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": [
|
8 |
+
"BartForConditionalGeneration"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.1,
|
11 |
+
"bos_token_id": 101,
|
12 |
+
"classif_dropout": 0.1,
|
13 |
+
"classifier_dropout": 0.0,
|
14 |
+
"d_model": 768,
|
15 |
+
"decoder_attention_heads": 12,
|
16 |
+
"decoder_ffn_dim": 3072,
|
17 |
+
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 6,
|
19 |
+
"decoder_start_token_id": 102,
|
20 |
+
"dropout": 0.1,
|
21 |
+
"early_stopping": true,
|
22 |
+
"encoder_attention_heads": 12,
|
23 |
+
"encoder_ffn_dim": 3072,
|
24 |
+
"encoder_layerdrop": 0.0,
|
25 |
+
"encoder_layers": 6,
|
26 |
+
"eos_token_id": 102,
|
27 |
+
"forced_eos_token_id": 102,
|
28 |
+
"gradient_checkpointing": false,
|
29 |
+
"id2label": {
|
30 |
+
"0": "LABEL_0",
|
31 |
+
"1": "LABEL_1",
|
32 |
+
"2": "LABEL_2"
|
33 |
+
},
|
34 |
+
"init_std": 0.02,
|
35 |
+
"is_encoder_decoder": true,
|
36 |
+
"label2id": {
|
37 |
+
"LABEL_0": 0,
|
38 |
+
"LABEL_1": 1,
|
39 |
+
"LABEL_2": 2
|
40 |
+
},
|
41 |
+
"max_position_embeddings": 1024,
|
42 |
+
"model_type": "bart",
|
43 |
+
"no_repeat_ngram_size": 3,
|
44 |
+
"normalize_before": false,
|
45 |
+
"normalize_embedding": true,
|
46 |
+
"num_beams": 4,
|
47 |
+
"num_hidden_layers": 6,
|
48 |
+
"pad_token_id": 0,
|
49 |
+
"scale_embedding": false,
|
50 |
+
"task_specific_params": {
|
51 |
+
"summarization": {
|
52 |
+
"length_penalty": 1.0,
|
53 |
+
"max_length": 128,
|
54 |
+
"min_length": 12,
|
55 |
+
"num_beams": 4
|
56 |
+
},
|
57 |
+
"summarization_cnn": {
|
58 |
+
"length_penalty": 2.0,
|
59 |
+
"max_length": 142,
|
60 |
+
"min_length": 56,
|
61 |
+
"num_beams": 4
|
62 |
+
},
|
63 |
+
"summarization_xsum": {
|
64 |
+
"length_penalty": 1.0,
|
65 |
+
"max_length": 62,
|
66 |
+
"min_length": 11,
|
67 |
+
"num_beams": 6
|
68 |
+
}
|
69 |
+
},
|
70 |
+
"tokenizer_class": "BertTokenizer",
|
71 |
+
"torch_dtype": "float32",
|
72 |
+
"transformers_version": "4.34.1",
|
73 |
+
"use_cache": true,
|
74 |
+
"vocab_size": 51453
|
75 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e746104f90c97ab764a87422ab1c71082c96ac2ad05b52891d85cceaeadd128
|
3 |
+
size 561625501
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "[CLS]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "[EOS]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "[MASK]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "[PAD]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "[SEP]",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "[UNK]",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,1524 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"104": {
|
44 |
+
"content": "[EOS]",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"51271": {
|
52 |
+
"content": "㖭",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": true,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": false
|
58 |
+
},
|
59 |
+
"51272": {
|
60 |
+
"content": "䊦",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": true,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": false
|
66 |
+
},
|
67 |
+
"51273": {
|
68 |
+
"content": "㨂",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": true,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": false
|
74 |
+
},
|
75 |
+
"51274": {
|
76 |
+
"content": "䁪",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": true,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": false
|
82 |
+
},
|
83 |
+
"51275": {
|
84 |
+
"content": "㴝",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": true,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": false
|
90 |
+
},
|
91 |
+
"51276": {
|
92 |
+
"content": "䑛",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": true,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": false
|
98 |
+
},
|
99 |
+
"51277": {
|
100 |
+
"content": "㽇",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": true,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": false
|
106 |
+
},
|
107 |
+
"51278": {
|
108 |
+
"content": "䟕",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": true,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": false
|
114 |
+
},
|
115 |
+
"51279": {
|
116 |
+
"content": "㢌",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": true,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": false
|
122 |
+
},
|
123 |
+
"51280": {
|
124 |
+
"content": "㗇",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": true,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": false
|
130 |
+
},
|
131 |
+
"51281": {
|
132 |
+
"content": "䉪",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": true,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": false
|
138 |
+
},
|
139 |
+
"51282": {
|
140 |
+
"content": "䐥",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": true,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": false
|
146 |
+
},
|
147 |
+
"51283": {
|
148 |
+
"content": "䘆",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": true,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": false
|
154 |
+
},
|
155 |
+
"51284": {
|
156 |
+
"content": "㘉",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": true,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": false
|
162 |
+
},
|
163 |
+
"51285": {
|
164 |
+
"content": "䚗",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": true,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": false
|
170 |
+
},
|
171 |
+
"51286": {
|
172 |
+
"content": "鰦",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": true,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": false
|
178 |
+
},
|
179 |
+
"51287": {
|
180 |
+
"content": "䄛",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": true,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": false
|
186 |
+
},
|
187 |
+
"51288": {
|
188 |
+
"content": "㔷",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": true,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": false
|
194 |
+
},
|
195 |
+
"51289": {
|
196 |
+
"content": "㗱",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": true,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": false
|
202 |
+
},
|
203 |
+
"51290": {
|
204 |
+
"content": "㭾",
|
205 |
+
"lstrip": false,
|
206 |
+
"normalized": true,
|
207 |
+
"rstrip": false,
|
208 |
+
"single_word": false,
|
209 |
+
"special": false
|
210 |
+
},
|
211 |
+
"51291": {
|
212 |
+
"content": "㗾",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": true,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": false,
|
217 |
+
"special": false
|
218 |
+
},
|
219 |
+
"51292": {
|
220 |
+
"content": "㧜",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": true,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": false,
|
225 |
+
"special": false
|
226 |
+
},
|
227 |
+
"51293": {
|
228 |
+
"content": "㴫",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": true,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
+
"special": false
|
234 |
+
},
|
235 |
+
"51294": {
|
236 |
+
"content": "䲒",
|
237 |
+
"lstrip": false,
|
238 |
+
"normalized": true,
|
239 |
+
"rstrip": false,
|
240 |
+
"single_word": false,
|
241 |
+
"special": false
|
242 |
+
},
|
243 |
+
"51295": {
|
244 |
+
"content": "㣒",
|
245 |
+
"lstrip": false,
|
246 |
+
"normalized": true,
|
247 |
+
"rstrip": false,
|
248 |
+
"single_word": false,
|
249 |
+
"special": false
|
250 |
+
},
|
251 |
+
"51296": {
|
252 |
+
"content": "䘀",
|
253 |
+
"lstrip": false,
|
254 |
+
"normalized": true,
|
255 |
+
"rstrip": false,
|
256 |
+
"single_word": false,
|
257 |
+
"special": false
|
258 |
+
},
|
259 |
+
"51297": {
|
260 |
+
"content": "㰸",
|
261 |
+
"lstrip": false,
|
262 |
+
"normalized": true,
|
263 |
+
"rstrip": false,
|
264 |
+
"single_word": false,
|
265 |
+
"special": false
|
266 |
+
},
|
267 |
+
"51298": {
|
268 |
+
"content": "䕊",
|
269 |
+
"lstrip": false,
|
270 |
+
"normalized": true,
|
271 |
+
"rstrip": false,
|
272 |
+
"single_word": false,
|
273 |
+
"special": false
|
274 |
+
},
|
275 |
+
"51299": {
|
276 |
+
"content": "㞓",
|
277 |
+
"lstrip": false,
|
278 |
+
"normalized": true,
|
279 |
+
"rstrip": false,
|
280 |
+
"single_word": false,
|
281 |
+
"special": false
|
282 |
+
},
|
283 |
+
"51300": {
|
284 |
+
"content": "䚔",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": true,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false,
|
289 |
+
"special": false
|
290 |
+
},
|
291 |
+
"51301": {
|
292 |
+
"content": "蠾",
|
293 |
+
"lstrip": false,
|
294 |
+
"normalized": true,
|
295 |
+
"rstrip": false,
|
296 |
+
"single_word": false,
|
297 |
+
"special": false
|
298 |
+
},
|
299 |
+
"51302": {
|
300 |
+
"content": "䭡",
|
301 |
+
"lstrip": false,
|
302 |
+
"normalized": true,
|
303 |
+
"rstrip": false,
|
304 |
+
"single_word": false,
|
305 |
+
"special": false
|
306 |
+
},
|
307 |
+
"51303": {
|
308 |
+
"content": "㵖",
|
309 |
+
"lstrip": false,
|
310 |
+
"normalized": true,
|
311 |
+
"rstrip": false,
|
312 |
+
"single_word": false,
|
313 |
+
"special": false
|
314 |
+
},
|
315 |
+
"51304": {
|
316 |
+
"content": "䵯",
|
317 |
+
"lstrip": false,
|
318 |
+
"normalized": true,
|
319 |
+
"rstrip": false,
|
320 |
+
"single_word": false,
|
321 |
+
"special": false
|
322 |
+
},
|
323 |
+
"51305": {
|
324 |
+
"content": "䋒",
|
325 |
+
"lstrip": false,
|
326 |
+
"normalized": true,
|
327 |
+
"rstrip": false,
|
328 |
+
"single_word": false,
|
329 |
+
"special": false
|
330 |
+
},
|
331 |
+
"51306": {
|
332 |
+
"content": "䐔",
|
333 |
+
"lstrip": false,
|
334 |
+
"normalized": true,
|
335 |
+
"rstrip": false,
|
336 |
+
"single_word": false,
|
337 |
+
"special": false
|
338 |
+
},
|
339 |
+
"51307": {
|
340 |
+
"content": "譈",
|
341 |
+
"lstrip": false,
|
342 |
+
"normalized": true,
|
343 |
+
"rstrip": false,
|
344 |
+
"single_word": false,
|
345 |
+
"special": false
|
346 |
+
},
|
347 |
+
"51308": {
|
348 |
+
"content": "䛮",
|
349 |
+
"lstrip": false,
|
350 |
+
"normalized": true,
|
351 |
+
"rstrip": false,
|
352 |
+
"single_word": false,
|
353 |
+
"special": false
|
354 |
+
},
|
355 |
+
"51309": {
|
356 |
+
"content": "䀳",
|
357 |
+
"lstrip": false,
|
358 |
+
"normalized": true,
|
359 |
+
"rstrip": false,
|
360 |
+
"single_word": false,
|
361 |
+
"special": false
|
362 |
+
},
|
363 |
+
"51310": {
|
364 |
+
"content": "㬮",
|
365 |
+
"lstrip": false,
|
366 |
+
"normalized": true,
|
367 |
+
"rstrip": false,
|
368 |
+
"single_word": false,
|
369 |
+
"special": false
|
370 |
+
},
|
371 |
+
"51311": {
|
372 |
+
"content": "䕼",
|
373 |
+
"lstrip": false,
|
374 |
+
"normalized": true,
|
375 |
+
"rstrip": false,
|
376 |
+
"single_word": false,
|
377 |
+
"special": false
|
378 |
+
},
|
379 |
+
"51312": {
|
380 |
+
"content": "䱏",
|
381 |
+
"lstrip": false,
|
382 |
+
"normalized": true,
|
383 |
+
"rstrip": false,
|
384 |
+
"single_word": false,
|
385 |
+
"special": false
|
386 |
+
},
|
387 |
+
"51313": {
|
388 |
+
"content": "䄮",
|
389 |
+
"lstrip": false,
|
390 |
+
"normalized": true,
|
391 |
+
"rstrip": false,
|
392 |
+
"single_word": false,
|
393 |
+
"special": false
|
394 |
+
},
|
395 |
+
"51314": {
|
396 |
+
"content": "䠮",
|
397 |
+
"lstrip": false,
|
398 |
+
"normalized": true,
|
399 |
+
"rstrip": false,
|
400 |
+
"single_word": false,
|
401 |
+
"special": false
|
402 |
+
},
|
403 |
+
"51315": {
|
404 |
+
"content": "㳮",
|
405 |
+
"lstrip": false,
|
406 |
+
"normalized": true,
|
407 |
+
"rstrip": false,
|
408 |
+
"single_word": false,
|
409 |
+
"special": false
|
410 |
+
},
|
411 |
+
"51316": {
|
412 |
+
"content": "㖥",
|
413 |
+
"lstrip": false,
|
414 |
+
"normalized": true,
|
415 |
+
"rstrip": false,
|
416 |
+
"single_word": false,
|
417 |
+
"special": false
|
418 |
+
},
|
419 |
+
"51317": {
|
420 |
+
"content": "籅",
|
421 |
+
"lstrip": false,
|
422 |
+
"normalized": true,
|
423 |
+
"rstrip": false,
|
424 |
+
"single_word": false,
|
425 |
+
"special": false
|
426 |
+
},
|
427 |
+
"51318": {
|
428 |
+
"content": "攳",
|
429 |
+
"lstrip": false,
|
430 |
+
"normalized": true,
|
431 |
+
"rstrip": false,
|
432 |
+
"single_word": false,
|
433 |
+
"special": false
|
434 |
+
},
|
435 |
+
"51319": {
|
436 |
+
"content": "㹵",
|
437 |
+
"lstrip": false,
|
438 |
+
"normalized": true,
|
439 |
+
"rstrip": false,
|
440 |
+
"single_word": false,
|
441 |
+
"special": false
|
442 |
+
},
|
443 |
+
"51320": {
|
444 |
+
"content": "䭮",
|
445 |
+
"lstrip": false,
|
446 |
+
"normalized": true,
|
447 |
+
"rstrip": false,
|
448 |
+
"single_word": false,
|
449 |
+
"special": false
|
450 |
+
},
|
451 |
+
"51321": {
|
452 |
+
"content": "䘳",
|
453 |
+
"lstrip": false,
|
454 |
+
"normalized": true,
|
455 |
+
"rstrip": false,
|
456 |
+
"single_word": false,
|
457 |
+
"special": false
|
458 |
+
},
|
459 |
+
"51322": {
|
460 |
+
"content": "䛷",
|
461 |
+
"lstrip": false,
|
462 |
+
"normalized": true,
|
463 |
+
"rstrip": false,
|
464 |
+
"single_word": false,
|
465 |
+
"special": false
|
466 |
+
},
|
467 |
+
"51323": {
|
468 |
+
"content": "㾝",
|
469 |
+
"lstrip": false,
|
470 |
+
"normalized": true,
|
471 |
+
"rstrip": false,
|
472 |
+
"single_word": false,
|
473 |
+
"special": false
|
474 |
+
},
|
475 |
+
"51324": {
|
476 |
+
"content": "䭽",
|
477 |
+
"lstrip": false,
|
478 |
+
"normalized": true,
|
479 |
+
"rstrip": false,
|
480 |
+
"single_word": false,
|
481 |
+
"special": false
|
482 |
+
},
|
483 |
+
"51325": {
|
484 |
+
"content": "㗋",
|
485 |
+
"lstrip": false,
|
486 |
+
"normalized": true,
|
487 |
+
"rstrip": false,
|
488 |
+
"single_word": false,
|
489 |
+
"special": false
|
490 |
+
},
|
491 |
+
"51326": {
|
492 |
+
"content": "㩕",
|
493 |
+
"lstrip": false,
|
494 |
+
"normalized": true,
|
495 |
+
"rstrip": false,
|
496 |
+
"single_word": false,
|
497 |
+
"special": false
|
498 |
+
},
|
499 |
+
"51327": {
|
500 |
+
"content": "㯰",
|
501 |
+
"lstrip": false,
|
502 |
+
"normalized": true,
|
503 |
+
"rstrip": false,
|
504 |
+
"single_word": false,
|
505 |
+
"special": false
|
506 |
+
},
|
507 |
+
"51328": {
|
508 |
+
"content": "㶺",
|
509 |
+
"lstrip": false,
|
510 |
+
"normalized": true,
|
511 |
+
"rstrip": false,
|
512 |
+
"single_word": false,
|
513 |
+
"special": false
|
514 |
+
},
|
515 |
+
"51329": {
|
516 |
+
"content": "䞟",
|
517 |
+
"lstrip": false,
|
518 |
+
"normalized": true,
|
519 |
+
"rstrip": false,
|
520 |
+
"single_word": false,
|
521 |
+
"special": false
|
522 |
+
},
|
523 |
+
"51330": {
|
524 |
+
"content": "㫗",
|
525 |
+
"lstrip": false,
|
526 |
+
"normalized": true,
|
527 |
+
"rstrip": false,
|
528 |
+
"single_word": false,
|
529 |
+
"special": false
|
530 |
+
},
|
531 |
+
"51331": {
|
532 |
+
"content": "㕷",
|
533 |
+
"lstrip": false,
|
534 |
+
"normalized": true,
|
535 |
+
"rstrip": false,
|
536 |
+
"single_word": false,
|
537 |
+
"special": false
|
538 |
+
},
|
539 |
+
"51332": {
|
540 |
+
"content": "㧧",
|
541 |
+
"lstrip": false,
|
542 |
+
"normalized": true,
|
543 |
+
"rstrip": false,
|
544 |
+
"single_word": false,
|
545 |
+
"special": false
|
546 |
+
},
|
547 |
+
"51333": {
|
548 |
+
"content": "䤄",
|
549 |
+
"lstrip": false,
|
550 |
+
"normalized": true,
|
551 |
+
"rstrip": false,
|
552 |
+
"single_word": false,
|
553 |
+
"special": false
|
554 |
+
},
|
555 |
+
"51334": {
|
556 |
+
"content": "㛱",
|
557 |
+
"lstrip": false,
|
558 |
+
"normalized": true,
|
559 |
+
"rstrip": false,
|
560 |
+
"single_word": false,
|
561 |
+
"special": false
|
562 |
+
},
|
563 |
+
"51335": {
|
564 |
+
"content": "㰮",
|
565 |
+
"lstrip": false,
|
566 |
+
"normalized": true,
|
567 |
+
"rstrip": false,
|
568 |
+
"single_word": false,
|
569 |
+
"special": false
|
570 |
+
},
|
571 |
+
"51336": {
|
572 |
+
"content": "㕍",
|
573 |
+
"lstrip": false,
|
574 |
+
"normalized": true,
|
575 |
+
"rstrip": false,
|
576 |
+
"single_word": false,
|
577 |
+
"special": false
|
578 |
+
},
|
579 |
+
"51337": {
|
580 |
+
"content": "䶵",
|
581 |
+
"lstrip": false,
|
582 |
+
"normalized": true,
|
583 |
+
"rstrip": false,
|
584 |
+
"single_word": false,
|
585 |
+
"special": false
|
586 |
+
},
|
587 |
+
"51338": {
|
588 |
+
"content": "㝿",
|
589 |
+
"lstrip": false,
|
590 |
+
"normalized": true,
|
591 |
+
"rstrip": false,
|
592 |
+
"single_word": false,
|
593 |
+
"special": false
|
594 |
+
},
|
595 |
+
"51339": {
|
596 |
+
"content": "㱒",
|
597 |
+
"lstrip": false,
|
598 |
+
"normalized": true,
|
599 |
+
"rstrip": false,
|
600 |
+
"single_word": false,
|
601 |
+
"special": false
|
602 |
+
},
|
603 |
+
"51340": {
|
604 |
+
"content": "鞝",
|
605 |
+
"lstrip": false,
|
606 |
+
"normalized": true,
|
607 |
+
"rstrip": false,
|
608 |
+
"single_word": false,
|
609 |
+
"special": false
|
610 |
+
},
|
611 |
+
"51341": {
|
612 |
+
"content": "㦨",
|
613 |
+
"lstrip": false,
|
614 |
+
"normalized": true,
|
615 |
+
"rstrip": false,
|
616 |
+
"single_word": false,
|
617 |
+
"special": false
|
618 |
+
},
|
619 |
+
"51342": {
|
620 |
+
"content": "㨘",
|
621 |
+
"lstrip": false,
|
622 |
+
"normalized": true,
|
623 |
+
"rstrip": false,
|
624 |
+
"single_word": false,
|
625 |
+
"special": false
|
626 |
+
},
|
627 |
+
"51343": {
|
628 |
+
"content": "䞾",
|
629 |
+
"lstrip": false,
|
630 |
+
"normalized": true,
|
631 |
+
"rstrip": false,
|
632 |
+
"single_word": false,
|
633 |
+
"special": false
|
634 |
+
},
|
635 |
+
"51344": {
|
636 |
+
"content": "䆭",
|
637 |
+
"lstrip": false,
|
638 |
+
"normalized": true,
|
639 |
+
"rstrip": false,
|
640 |
+
"single_word": false,
|
641 |
+
"special": false
|
642 |
+
},
|
643 |
+
"51345": {
|
644 |
+
"content": "䭃",
|
645 |
+
"lstrip": false,
|
646 |
+
"normalized": true,
|
647 |
+
"rstrip": false,
|
648 |
+
"single_word": false,
|
649 |
+
"special": false
|
650 |
+
},
|
651 |
+
"51346": {
|
652 |
+
"content": "㕇",
|
653 |
+
"lstrip": false,
|
654 |
+
"normalized": true,
|
655 |
+
"rstrip": false,
|
656 |
+
"single_word": false,
|
657 |
+
"special": false
|
658 |
+
},
|
659 |
+
"51347": {
|
660 |
+
"content": "騇",
|
661 |
+
"lstrip": false,
|
662 |
+
"normalized": true,
|
663 |
+
"rstrip": false,
|
664 |
+
"single_word": false,
|
665 |
+
"special": false
|
666 |
+
},
|
667 |
+
"51348": {
|
668 |
+
"content": "䰢",
|
669 |
+
"lstrip": false,
|
670 |
+
"normalized": true,
|
671 |
+
"rstrip": false,
|
672 |
+
"single_word": false,
|
673 |
+
"special": false
|
674 |
+
},
|
675 |
+
"51349": {
|
676 |
+
"content": "䦞",
|
677 |
+
"lstrip": false,
|
678 |
+
"normalized": true,
|
679 |
+
"rstrip": false,
|
680 |
+
"single_word": false,
|
681 |
+
"special": false
|
682 |
+
},
|
683 |
+
"51350": {
|
684 |
+
"content": "䯧",
|
685 |
+
"lstrip": false,
|
686 |
+
"normalized": true,
|
687 |
+
"rstrip": false,
|
688 |
+
"single_word": false,
|
689 |
+
"special": false
|
690 |
+
},
|
691 |
+
"51351": {
|
692 |
+
"content": "㲈",
|
693 |
+
"lstrip": false,
|
694 |
+
"normalized": true,
|
695 |
+
"rstrip": false,
|
696 |
+
"single_word": false,
|
697 |
+
"special": false
|
698 |
+
},
|
699 |
+
"51352": {
|
700 |
+
"content": "㸛",
|
701 |
+
"lstrip": false,
|
702 |
+
"normalized": true,
|
703 |
+
"rstrip": false,
|
704 |
+
"single_word": false,
|
705 |
+
"special": false
|
706 |
+
},
|
707 |
+
"51353": {
|
708 |
+
"content": "㩻",
|
709 |
+
"lstrip": false,
|
710 |
+
"normalized": true,
|
711 |
+
"rstrip": false,
|
712 |
+
"single_word": false,
|
713 |
+
"special": false
|
714 |
+
},
|
715 |
+
"51354": {
|
716 |
+
"content": "䒭",
|
717 |
+
"lstrip": false,
|
718 |
+
"normalized": true,
|
719 |
+
"rstrip": false,
|
720 |
+
"single_word": false,
|
721 |
+
"special": false
|
722 |
+
},
|
723 |
+
"51355": {
|
724 |
+
"content": "䭋",
|
725 |
+
"lstrip": false,
|
726 |
+
"normalized": true,
|
727 |
+
"rstrip": false,
|
728 |
+
"single_word": false,
|
729 |
+
"special": false
|
730 |
+
},
|
731 |
+
"51356": {
|
732 |
+
"content": "䱰",
|
733 |
+
"lstrip": false,
|
734 |
+
"normalized": true,
|
735 |
+
"rstrip": false,
|
736 |
+
"single_word": false,
|
737 |
+
"special": false
|
738 |
+
},
|
739 |
+
"51357": {
|
740 |
+
"content": "㶦",
|
741 |
+
"lstrip": false,
|
742 |
+
"normalized": true,
|
743 |
+
"rstrip": false,
|
744 |
+
"single_word": false,
|
745 |
+
"special": false
|
746 |
+
},
|
747 |
+
"51358": {
|
748 |
+
"content": "䏺",
|
749 |
+
"lstrip": false,
|
750 |
+
"normalized": true,
|
751 |
+
"rstrip": false,
|
752 |
+
"single_word": false,
|
753 |
+
"special": false
|
754 |
+
},
|
755 |
+
"51359": {
|
756 |
+
"content": "㢜",
|
757 |
+
"lstrip": false,
|
758 |
+
"normalized": true,
|
759 |
+
"rstrip": false,
|
760 |
+
"single_word": false,
|
761 |
+
"special": false
|
762 |
+
},
|
763 |
+
"51360": {
|
764 |
+
"content": "䩐",
|
765 |
+
"lstrip": false,
|
766 |
+
"normalized": true,
|
767 |
+
"rstrip": false,
|
768 |
+
"single_word": false,
|
769 |
+
"special": false
|
770 |
+
},
|
771 |
+
"51361": {
|
772 |
+
"content": "㭛",
|
773 |
+
"lstrip": false,
|
774 |
+
"normalized": true,
|
775 |
+
"rstrip": false,
|
776 |
+
"single_word": false,
|
777 |
+
"special": false
|
778 |
+
},
|
779 |
+
"51362": {
|
780 |
+
"content": "䌟",
|
781 |
+
"lstrip": false,
|
782 |
+
"normalized": true,
|
783 |
+
"rstrip": false,
|
784 |
+
"single_word": false,
|
785 |
+
"special": false
|
786 |
+
},
|
787 |
+
"51363": {
|
788 |
+
"content": "㮇",
|
789 |
+
"lstrip": false,
|
790 |
+
"normalized": true,
|
791 |
+
"rstrip": false,
|
792 |
+
"single_word": false,
|
793 |
+
"special": false
|
794 |
+
},
|
795 |
+
"51364": {
|
796 |
+
"content": "㨾",
|
797 |
+
"lstrip": false,
|
798 |
+
"normalized": true,
|
799 |
+
"rstrip": false,
|
800 |
+
"single_word": false,
|
801 |
+
"special": false
|
802 |
+
},
|
803 |
+
"51365": {
|
804 |
+
"content": "㑃",
|
805 |
+
"lstrip": false,
|
806 |
+
"normalized": true,
|
807 |
+
"rstrip": false,
|
808 |
+
"single_word": false,
|
809 |
+
"special": false
|
810 |
+
},
|
811 |
+
"51366": {
|
812 |
+
"content": "㱱",
|
813 |
+
"lstrip": false,
|
814 |
+
"normalized": true,
|
815 |
+
"rstrip": false,
|
816 |
+
"single_word": false,
|
817 |
+
"special": false
|
818 |
+
},
|
819 |
+
"51367": {
|
820 |
+
"content": "䰣",
|
821 |
+
"lstrip": false,
|
822 |
+
"normalized": true,
|
823 |
+
"rstrip": false,
|
824 |
+
"single_word": false,
|
825 |
+
"special": false
|
826 |
+
},
|
827 |
+
"51368": {
|
828 |
+
"content": "䀆",
|
829 |
+
"lstrip": false,
|
830 |
+
"normalized": true,
|
831 |
+
"rstrip": false,
|
832 |
+
"single_word": false,
|
833 |
+
"special": false
|
834 |
+
},
|
835 |
+
"51369": {
|
836 |
+
"content": "䊵",
|
837 |
+
"lstrip": false,
|
838 |
+
"normalized": true,
|
839 |
+
"rstrip": false,
|
840 |
+
"single_word": false,
|
841 |
+
"special": false
|
842 |
+
},
|
843 |
+
"51370": {
|
844 |
+
"content": "㹒",
|
845 |
+
"lstrip": false,
|
846 |
+
"normalized": true,
|
847 |
+
"rstrip": false,
|
848 |
+
"single_word": false,
|
849 |
+
"special": false
|
850 |
+
},
|
851 |
+
"51371": {
|
852 |
+
"content": "䁵",
|
853 |
+
"lstrip": false,
|
854 |
+
"normalized": true,
|
855 |
+
"rstrip": false,
|
856 |
+
"single_word": false,
|
857 |
+
"special": false
|
858 |
+
},
|
859 |
+
"51372": {
|
860 |
+
"content": "䞨",
|
861 |
+
"lstrip": false,
|
862 |
+
"normalized": true,
|
863 |
+
"rstrip": false,
|
864 |
+
"single_word": false,
|
865 |
+
"special": false
|
866 |
+
},
|
867 |
+
"51373": {
|
868 |
+
"content": "饇",
|
869 |
+
"lstrip": false,
|
870 |
+
"normalized": true,
|
871 |
+
"rstrip": false,
|
872 |
+
"single_word": false,
|
873 |
+
"special": false
|
874 |
+
},
|
875 |
+
"51374": {
|
876 |
+
"content": "㹾",
|
877 |
+
"lstrip": false,
|
878 |
+
"normalized": true,
|
879 |
+
"rstrip": false,
|
880 |
+
"single_word": false,
|
881 |
+
"special": false
|
882 |
+
},
|
883 |
+
"51375": {
|
884 |
+
"content": "䣸",
|
885 |
+
"lstrip": false,
|
886 |
+
"normalized": true,
|
887 |
+
"rstrip": false,
|
888 |
+
"single_word": false,
|
889 |
+
"special": false
|
890 |
+
},
|
891 |
+
"51376": {
|
892 |
+
"content": "㝫",
|
893 |
+
"lstrip": false,
|
894 |
+
"normalized": true,
|
895 |
+
"rstrip": false,
|
896 |
+
"single_word": false,
|
897 |
+
"special": false
|
898 |
+
},
|
899 |
+
"51377": {
|
900 |
+
"content": "㵞",
|
901 |
+
"lstrip": false,
|
902 |
+
"normalized": true,
|
903 |
+
"rstrip": false,
|
904 |
+
"single_word": false,
|
905 |
+
"special": false
|
906 |
+
},
|
907 |
+
"51378": {
|
908 |
+
"content": "㵕",
|
909 |
+
"lstrip": false,
|
910 |
+
"normalized": true,
|
911 |
+
"rstrip": false,
|
912 |
+
"single_word": false,
|
913 |
+
"special": false
|
914 |
+
},
|
915 |
+
"51379": {
|
916 |
+
"content": "䯡",
|
917 |
+
"lstrip": false,
|
918 |
+
"normalized": true,
|
919 |
+
"rstrip": false,
|
920 |
+
"single_word": false,
|
921 |
+
"special": false
|
922 |
+
},
|
923 |
+
"51380": {
|
924 |
+
"content": "䁷",
|
925 |
+
"lstrip": false,
|
926 |
+
"normalized": true,
|
927 |
+
"rstrip": false,
|
928 |
+
"single_word": false,
|
929 |
+
"special": false
|
930 |
+
},
|
931 |
+
"51381": {
|
932 |
+
"content": "藀",
|
933 |
+
"lstrip": false,
|
934 |
+
"normalized": true,
|
935 |
+
"rstrip": false,
|
936 |
+
"single_word": false,
|
937 |
+
"special": false
|
938 |
+
},
|
939 |
+
"51382": {
|
940 |
+
"content": "㝙",
|
941 |
+
"lstrip": false,
|
942 |
+
"normalized": true,
|
943 |
+
"rstrip": false,
|
944 |
+
"single_word": false,
|
945 |
+
"special": false
|
946 |
+
},
|
947 |
+
"51383": {
|
948 |
+
"content": "㭂",
|
949 |
+
"lstrip": false,
|
950 |
+
"normalized": true,
|
951 |
+
"rstrip": false,
|
952 |
+
"single_word": false,
|
953 |
+
"special": false
|
954 |
+
},
|
955 |
+
"51384": {
|
956 |
+
"content": "䁓",
|
957 |
+
"lstrip": false,
|
958 |
+
"normalized": true,
|
959 |
+
"rstrip": false,
|
960 |
+
"single_word": false,
|
961 |
+
"special": false
|
962 |
+
},
|
963 |
+
"51385": {
|
964 |
+
"content": "㲻",
|
965 |
+
"lstrip": false,
|
966 |
+
"normalized": true,
|
967 |
+
"rstrip": false,
|
968 |
+
"single_word": false,
|
969 |
+
"special": false
|
970 |
+
},
|
971 |
+
"51386": {
|
972 |
+
"content": "䊯",
|
973 |
+
"lstrip": false,
|
974 |
+
"normalized": true,
|
975 |
+
"rstrip": false,
|
976 |
+
"single_word": false,
|
977 |
+
"special": false
|
978 |
+
},
|
979 |
+
"51387": {
|
980 |
+
"content": "㰹",
|
981 |
+
"lstrip": false,
|
982 |
+
"normalized": true,
|
983 |
+
"rstrip": false,
|
984 |
+
"single_word": false,
|
985 |
+
"special": false
|
986 |
+
},
|
987 |
+
"51388": {
|
988 |
+
"content": "㥶",
|
989 |
+
"lstrip": false,
|
990 |
+
"normalized": true,
|
991 |
+
"rstrip": false,
|
992 |
+
"single_word": false,
|
993 |
+
"special": false
|
994 |
+
},
|
995 |
+
"51389": {
|
996 |
+
"content": "㙒",
|
997 |
+
"lstrip": false,
|
998 |
+
"normalized": true,
|
999 |
+
"rstrip": false,
|
1000 |
+
"single_word": false,
|
1001 |
+
"special": false
|
1002 |
+
},
|
1003 |
+
"51390": {
|
1004 |
+
"content": "㤟",
|
1005 |
+
"lstrip": false,
|
1006 |
+
"normalized": true,
|
1007 |
+
"rstrip": false,
|
1008 |
+
"single_word": false,
|
1009 |
+
"special": false
|
1010 |
+
},
|
1011 |
+
"51391": {
|
1012 |
+
"content": "䦥",
|
1013 |
+
"lstrip": false,
|
1014 |
+
"normalized": true,
|
1015 |
+
"rstrip": false,
|
1016 |
+
"single_word": false,
|
1017 |
+
"special": false
|
1018 |
+
},
|
1019 |
+
"51392": {
|
1020 |
+
"content": "㭬",
|
1021 |
+
"lstrip": false,
|
1022 |
+
"normalized": true,
|
1023 |
+
"rstrip": false,
|
1024 |
+
"single_word": false,
|
1025 |
+
"special": false
|
1026 |
+
},
|
1027 |
+
"51393": {
|
1028 |
+
"content": "㑰",
|
1029 |
+
"lstrip": false,
|
1030 |
+
"normalized": true,
|
1031 |
+
"rstrip": false,
|
1032 |
+
"single_word": false,
|
1033 |
+
"special": false
|
1034 |
+
},
|
1035 |
+
"51394": {
|
1036 |
+
"content": "㤳",
|
1037 |
+
"lstrip": false,
|
1038 |
+
"normalized": true,
|
1039 |
+
"rstrip": false,
|
1040 |
+
"single_word": false,
|
1041 |
+
"special": false
|
1042 |
+
},
|
1043 |
+
"51395": {
|
1044 |
+
"content": "䵎",
|
1045 |
+
"lstrip": false,
|
1046 |
+
"normalized": true,
|
1047 |
+
"rstrip": false,
|
1048 |
+
"single_word": false,
|
1049 |
+
"special": false
|
1050 |
+
},
|
1051 |
+
"51396": {
|
1052 |
+
"content": "䄒",
|
1053 |
+
"lstrip": false,
|
1054 |
+
"normalized": true,
|
1055 |
+
"rstrip": false,
|
1056 |
+
"single_word": false,
|
1057 |
+
"special": false
|
1058 |
+
},
|
1059 |
+
"51397": {
|
1060 |
+
"content": "䰺",
|
1061 |
+
"lstrip": false,
|
1062 |
+
"normalized": true,
|
1063 |
+
"rstrip": false,
|
1064 |
+
"single_word": false,
|
1065 |
+
"special": false
|
1066 |
+
},
|
1067 |
+
"51398": {
|
1068 |
+
"content": "㬢",
|
1069 |
+
"lstrip": false,
|
1070 |
+
"normalized": true,
|
1071 |
+
"rstrip": false,
|
1072 |
+
"single_word": false,
|
1073 |
+
"special": false
|
1074 |
+
},
|
1075 |
+
"51399": {
|
1076 |
+
"content": "䈢",
|
1077 |
+
"lstrip": false,
|
1078 |
+
"normalized": true,
|
1079 |
+
"rstrip": false,
|
1080 |
+
"single_word": false,
|
1081 |
+
"special": false
|
1082 |
+
},
|
1083 |
+
"51400": {
|
1084 |
+
"content": "䏙",
|
1085 |
+
"lstrip": false,
|
1086 |
+
"normalized": true,
|
1087 |
+
"rstrip": false,
|
1088 |
+
"single_word": false,
|
1089 |
+
"special": false
|
1090 |
+
},
|
1091 |
+
"51401": {
|
1092 |
+
"content": "㤓",
|
1093 |
+
"lstrip": false,
|
1094 |
+
"normalized": true,
|
1095 |
+
"rstrip": false,
|
1096 |
+
"single_word": false,
|
1097 |
+
"special": false
|
1098 |
+
},
|
1099 |
+
"51402": {
|
1100 |
+
"content": "㔁",
|
1101 |
+
"lstrip": false,
|
1102 |
+
"normalized": true,
|
1103 |
+
"rstrip": false,
|
1104 |
+
"single_word": false,
|
1105 |
+
"special": false
|
1106 |
+
},
|
1107 |
+
"51403": {
|
1108 |
+
"content": "㵻",
|
1109 |
+
"lstrip": false,
|
1110 |
+
"normalized": true,
|
1111 |
+
"rstrip": false,
|
1112 |
+
"single_word": false,
|
1113 |
+
"special": false
|
1114 |
+
},
|
1115 |
+
"51404": {
|
1116 |
+
"content": "㪹",
|
1117 |
+
"lstrip": false,
|
1118 |
+
"normalized": true,
|
1119 |
+
"rstrip": false,
|
1120 |
+
"single_word": false,
|
1121 |
+
"special": false
|
1122 |
+
},
|
1123 |
+
"51405": {
|
1124 |
+
"content": "㓟",
|
1125 |
+
"lstrip": false,
|
1126 |
+
"normalized": true,
|
1127 |
+
"rstrip": false,
|
1128 |
+
"single_word": false,
|
1129 |
+
"special": false
|
1130 |
+
},
|
1131 |
+
"51406": {
|
1132 |
+
"content": "㛻",
|
1133 |
+
"lstrip": false,
|
1134 |
+
"normalized": true,
|
1135 |
+
"rstrip": false,
|
1136 |
+
"single_word": false,
|
1137 |
+
"special": false
|
1138 |
+
},
|
1139 |
+
"51407": {
|
1140 |
+
"content": "䉵",
|
1141 |
+
"lstrip": false,
|
1142 |
+
"normalized": true,
|
1143 |
+
"rstrip": false,
|
1144 |
+
"single_word": false,
|
1145 |
+
"special": false
|
1146 |
+
},
|
1147 |
+
"51408": {
|
1148 |
+
"content": "䵜",
|
1149 |
+
"lstrip": false,
|
1150 |
+
"normalized": true,
|
1151 |
+
"rstrip": false,
|
1152 |
+
"single_word": false,
|
1153 |
+
"special": false
|
1154 |
+
},
|
1155 |
+
"51409": {
|
1156 |
+
"content": "䄪",
|
1157 |
+
"lstrip": false,
|
1158 |
+
"normalized": true,
|
1159 |
+
"rstrip": false,
|
1160 |
+
"single_word": false,
|
1161 |
+
"special": false
|
1162 |
+
},
|
1163 |
+
"51410": {
|
1164 |
+
"content": "㭋",
|
1165 |
+
"lstrip": false,
|
1166 |
+
"normalized": true,
|
1167 |
+
"rstrip": false,
|
1168 |
+
"single_word": false,
|
1169 |
+
"special": false
|
1170 |
+
},
|
1171 |
+
"51411": {
|
1172 |
+
"content": "㑭",
|
1173 |
+
"lstrip": false,
|
1174 |
+
"normalized": true,
|
1175 |
+
"rstrip": false,
|
1176 |
+
"single_word": false,
|
1177 |
+
"special": false
|
1178 |
+
},
|
1179 |
+
"51412": {
|
1180 |
+
"content": "䀨",
|
1181 |
+
"lstrip": false,
|
1182 |
+
"normalized": true,
|
1183 |
+
"rstrip": false,
|
1184 |
+
"single_word": false,
|
1185 |
+
"special": false
|
1186 |
+
},
|
1187 |
+
"51413": {
|
1188 |
+
"content": "嘺",
|
1189 |
+
"lstrip": false,
|
1190 |
+
"normalized": true,
|
1191 |
+
"rstrip": false,
|
1192 |
+
"single_word": false,
|
1193 |
+
"special": false
|
1194 |
+
},
|
1195 |
+
"51414": {
|
1196 |
+
"content": "㸀",
|
1197 |
+
"lstrip": false,
|
1198 |
+
"normalized": true,
|
1199 |
+
"rstrip": false,
|
1200 |
+
"single_word": false,
|
1201 |
+
"special": false
|
1202 |
+
},
|
1203 |
+
"51415": {
|
1204 |
+
"content": "䈟",
|
1205 |
+
"lstrip": false,
|
1206 |
+
"normalized": true,
|
1207 |
+
"rstrip": false,
|
1208 |
+
"single_word": false,
|
1209 |
+
"special": false
|
1210 |
+
},
|
1211 |
+
"51416": {
|
1212 |
+
"content": "㚲",
|
1213 |
+
"lstrip": false,
|
1214 |
+
"normalized": true,
|
1215 |
+
"rstrip": false,
|
1216 |
+
"single_word": false,
|
1217 |
+
"special": false
|
1218 |
+
},
|
1219 |
+
"51417": {
|
1220 |
+
"content": "㞜",
|
1221 |
+
"lstrip": false,
|
1222 |
+
"normalized": true,
|
1223 |
+
"rstrip": false,
|
1224 |
+
"single_word": false,
|
1225 |
+
"special": false
|
1226 |
+
},
|
1227 |
+
"51418": {
|
1228 |
+
"content": "藬",
|
1229 |
+
"lstrip": false,
|
1230 |
+
"normalized": true,
|
1231 |
+
"rstrip": false,
|
1232 |
+
"single_word": false,
|
1233 |
+
"special": false
|
1234 |
+
},
|
1235 |
+
"51419": {
|
1236 |
+
"content": "䕱",
|
1237 |
+
"lstrip": false,
|
1238 |
+
"normalized": true,
|
1239 |
+
"rstrip": false,
|
1240 |
+
"single_word": false,
|
1241 |
+
"special": false
|
1242 |
+
},
|
1243 |
+
"51420": {
|
1244 |
+
"content": "㗻",
|
1245 |
+
"lstrip": false,
|
1246 |
+
"normalized": true,
|
1247 |
+
"rstrip": false,
|
1248 |
+
"single_word": false,
|
1249 |
+
"special": false
|
1250 |
+
},
|
1251 |
+
"51421": {
|
1252 |
+
"content": "䩢",
|
1253 |
+
"lstrip": false,
|
1254 |
+
"normalized": true,
|
1255 |
+
"rstrip": false,
|
1256 |
+
"single_word": false,
|
1257 |
+
"special": false
|
1258 |
+
},
|
1259 |
+
"51422": {
|
1260 |
+
"content": "齴",
|
1261 |
+
"lstrip": false,
|
1262 |
+
"normalized": true,
|
1263 |
+
"rstrip": false,
|
1264 |
+
"single_word": false,
|
1265 |
+
"special": false
|
1266 |
+
},
|
1267 |
+
"51423": {
|
1268 |
+
"content": "䪐",
|
1269 |
+
"lstrip": false,
|
1270 |
+
"normalized": true,
|
1271 |
+
"rstrip": false,
|
1272 |
+
"single_word": false,
|
1273 |
+
"special": false
|
1274 |
+
},
|
1275 |
+
"51424": {
|
1276 |
+
"content": "㕃",
|
1277 |
+
"lstrip": false,
|
1278 |
+
"normalized": true,
|
1279 |
+
"rstrip": false,
|
1280 |
+
"single_word": false,
|
1281 |
+
"special": false
|
1282 |
+
},
|
1283 |
+
"51425": {
|
1284 |
+
"content": "䰝",
|
1285 |
+
"lstrip": false,
|
1286 |
+
"normalized": true,
|
1287 |
+
"rstrip": false,
|
1288 |
+
"single_word": false,
|
1289 |
+
"special": false
|
1290 |
+
},
|
1291 |
+
"51426": {
|
1292 |
+
"content": "䶡",
|
1293 |
+
"lstrip": false,
|
1294 |
+
"normalized": true,
|
1295 |
+
"rstrip": false,
|
1296 |
+
"single_word": false,
|
1297 |
+
"special": false
|
1298 |
+
},
|
1299 |
+
"51427": {
|
1300 |
+
"content": "䠊",
|
1301 |
+
"lstrip": false,
|
1302 |
+
"normalized": true,
|
1303 |
+
"rstrip": false,
|
1304 |
+
"single_word": false,
|
1305 |
+
"special": false
|
1306 |
+
},
|
1307 |
+
"51428": {
|
1308 |
+
"content": "㓋",
|
1309 |
+
"lstrip": false,
|
1310 |
+
"normalized": true,
|
1311 |
+
"rstrip": false,
|
1312 |
+
"single_word": false,
|
1313 |
+
"special": false
|
1314 |
+
},
|
1315 |
+
"51429": {
|
1316 |
+
"content": "躷",
|
1317 |
+
"lstrip": false,
|
1318 |
+
"normalized": true,
|
1319 |
+
"rstrip": false,
|
1320 |
+
"single_word": false,
|
1321 |
+
"special": false
|
1322 |
+
},
|
1323 |
+
"51430": {
|
1324 |
+
"content": "㓽",
|
1325 |
+
"lstrip": false,
|
1326 |
+
"normalized": true,
|
1327 |
+
"rstrip": false,
|
1328 |
+
"single_word": false,
|
1329 |
+
"special": false
|
1330 |
+
},
|
1331 |
+
"51431": {
|
1332 |
+
"content": "㽂",
|
1333 |
+
"lstrip": false,
|
1334 |
+
"normalized": true,
|
1335 |
+
"rstrip": false,
|
1336 |
+
"single_word": false,
|
1337 |
+
"special": false
|
1338 |
+
},
|
1339 |
+
"51432": {
|
1340 |
+
"content": "䝟",
|
1341 |
+
"lstrip": false,
|
1342 |
+
"normalized": true,
|
1343 |
+
"rstrip": false,
|
1344 |
+
"single_word": false,
|
1345 |
+
"special": false
|
1346 |
+
},
|
1347 |
+
"51433": {
|
1348 |
+
"content": "䧐",
|
1349 |
+
"lstrip": false,
|
1350 |
+
"normalized": true,
|
1351 |
+
"rstrip": false,
|
1352 |
+
"single_word": false,
|
1353 |
+
"special": false
|
1354 |
+
},
|
1355 |
+
"51434": {
|
1356 |
+
"content": "邭",
|
1357 |
+
"lstrip": false,
|
1358 |
+
"normalized": true,
|
1359 |
+
"rstrip": false,
|
1360 |
+
"single_word": false,
|
1361 |
+
"special": false
|
1362 |
+
},
|
1363 |
+
"51435": {
|
1364 |
+
"content": "㢸",
|
1365 |
+
"lstrip": false,
|
1366 |
+
"normalized": true,
|
1367 |
+
"rstrip": false,
|
1368 |
+
"single_word": false,
|
1369 |
+
"special": false
|
1370 |
+
},
|
1371 |
+
"51436": {
|
1372 |
+
"content": "䅤",
|
1373 |
+
"lstrip": false,
|
1374 |
+
"normalized": true,
|
1375 |
+
"rstrip": false,
|
1376 |
+
"single_word": false,
|
1377 |
+
"special": false
|
1378 |
+
},
|
1379 |
+
"51437": {
|
1380 |
+
"content": "㿺",
|
1381 |
+
"lstrip": false,
|
1382 |
+
"normalized": true,
|
1383 |
+
"rstrip": false,
|
1384 |
+
"single_word": false,
|
1385 |
+
"special": false
|
1386 |
+
},
|
1387 |
+
"51438": {
|
1388 |
+
"content": "㣜",
|
1389 |
+
"lstrip": false,
|
1390 |
+
"normalized": true,
|
1391 |
+
"rstrip": false,
|
1392 |
+
"single_word": false,
|
1393 |
+
"special": false
|
1394 |
+
},
|
1395 |
+
"51439": {
|
1396 |
+
"content": "䮺",
|
1397 |
+
"lstrip": false,
|
1398 |
+
"normalized": true,
|
1399 |
+
"rstrip": false,
|
1400 |
+
"single_word": false,
|
1401 |
+
"special": false
|
1402 |
+
},
|
1403 |
+
"51440": {
|
1404 |
+
"content": "㗳",
|
1405 |
+
"lstrip": false,
|
1406 |
+
"normalized": true,
|
1407 |
+
"rstrip": false,
|
1408 |
+
"single_word": false,
|
1409 |
+
"special": false
|
1410 |
+
},
|
1411 |
+
"51441": {
|
1412 |
+
"content": "㾓",
|
1413 |
+
"lstrip": false,
|
1414 |
+
"normalized": true,
|
1415 |
+
"rstrip": false,
|
1416 |
+
"single_word": false,
|
1417 |
+
"special": false
|
1418 |
+
},
|
1419 |
+
"51442": {
|
1420 |
+
"content": "嚝",
|
1421 |
+
"lstrip": false,
|
1422 |
+
"normalized": true,
|
1423 |
+
"rstrip": false,
|
1424 |
+
"single_word": false,
|
1425 |
+
"special": false
|
1426 |
+
},
|
1427 |
+
"51443": {
|
1428 |
+
"content": "㩙",
|
1429 |
+
"lstrip": false,
|
1430 |
+
"normalized": true,
|
1431 |
+
"rstrip": false,
|
1432 |
+
"single_word": false,
|
1433 |
+
"special": false
|
1434 |
+
},
|
1435 |
+
"51444": {
|
1436 |
+
"content": "䉔",
|
1437 |
+
"lstrip": false,
|
1438 |
+
"normalized": true,
|
1439 |
+
"rstrip": false,
|
1440 |
+
"single_word": false,
|
1441 |
+
"special": false
|
1442 |
+
},
|
1443 |
+
"51445": {
|
1444 |
+
"content": "䂾",
|
1445 |
+
"lstrip": false,
|
1446 |
+
"normalized": true,
|
1447 |
+
"rstrip": false,
|
1448 |
+
"single_word": false,
|
1449 |
+
"special": false
|
1450 |
+
},
|
1451 |
+
"51446": {
|
1452 |
+
"content": "贉",
|
1453 |
+
"lstrip": false,
|
1454 |
+
"normalized": true,
|
1455 |
+
"rstrip": false,
|
1456 |
+
"single_word": false,
|
1457 |
+
"special": false
|
1458 |
+
},
|
1459 |
+
"51447": {
|
1460 |
+
"content": "㾘",
|
1461 |
+
"lstrip": false,
|
1462 |
+
"normalized": true,
|
1463 |
+
"rstrip": false,
|
1464 |
+
"single_word": false,
|
1465 |
+
"special": false
|
1466 |
+
},
|
1467 |
+
"51448": {
|
1468 |
+
"content": "㧵",
|
1469 |
+
"lstrip": false,
|
1470 |
+
"normalized": true,
|
1471 |
+
"rstrip": false,
|
1472 |
+
"single_word": false,
|
1473 |
+
"special": false
|
1474 |
+
},
|
1475 |
+
"51449": {
|
1476 |
+
"content": "䥚",
|
1477 |
+
"lstrip": false,
|
1478 |
+
"normalized": true,
|
1479 |
+
"rstrip": false,
|
1480 |
+
"single_word": false,
|
1481 |
+
"special": false
|
1482 |
+
},
|
1483 |
+
"51450": {
|
1484 |
+
"content": "䵦",
|
1485 |
+
"lstrip": false,
|
1486 |
+
"normalized": true,
|
1487 |
+
"rstrip": false,
|
1488 |
+
"single_word": false,
|
1489 |
+
"special": false
|
1490 |
+
},
|
1491 |
+
"51451": {
|
1492 |
+
"content": "䧬",
|
1493 |
+
"lstrip": false,
|
1494 |
+
"normalized": true,
|
1495 |
+
"rstrip": false,
|
1496 |
+
"single_word": false,
|
1497 |
+
"special": false
|
1498 |
+
},
|
1499 |
+
"51452": {
|
1500 |
+
"content": "䃛",
|
1501 |
+
"lstrip": false,
|
1502 |
+
"normalized": true,
|
1503 |
+
"rstrip": false,
|
1504 |
+
"single_word": false,
|
1505 |
+
"special": false
|
1506 |
+
}
|
1507 |
+
},
|
1508 |
+
"bos_token": "[CLS]",
|
1509 |
+
"clean_up_tokenization_spaces": true,
|
1510 |
+
"cls_token": "[CLS]",
|
1511 |
+
"do_basic_tokenize": true,
|
1512 |
+
"do_lower_case": false,
|
1513 |
+
"eos_token": "[EOS]",
|
1514 |
+
"mask_token": "[MASK]",
|
1515 |
+
"model_max_length": 1000000000000000019884624838656,
|
1516 |
+
"never_split": null,
|
1517 |
+
"pad_token": "[PAD]",
|
1518 |
+
"sep_token": "[SEP]",
|
1519 |
+
"strip_accents": null,
|
1520 |
+
"tokenize_chinese_chars": true,
|
1521 |
+
"tokenizer_class": "BertTokenizer",
|
1522 |
+
"unk_token": "[UNK]",
|
1523 |
+
"use_fast": true
|
1524 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35951e9d751768cf8d7a3492e79ed6ee7ea14a547a15ad5ab6ffc24599c1c5fe
|
3 |
+
size 4283
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|