Upload folder using huggingface_hub
Browse files- special_tokens_map.json +7 -49
- test/added_tokens.json +1011 -0
- test/chat_template.jinja +24 -0
- test/special_tokens_map.json +1062 -0
- test/tokenization_ernie4_5.py +373 -0
- test/tokenizer.model +3 -0
- test/tokenizer_config.json +0 -0
- tokenizer.json +2 -2
- tokenizer_config.json +3 -91
special_tokens_map.json
CHANGED
@@ -1010,53 +1010,11 @@
|
|
1010 |
"<|CROP_ROW_SEP|>",
|
1011 |
"<|IMAGE_SEP|>"
|
1012 |
],
|
1013 |
-
"bos_token":
|
1014 |
-
|
1015 |
-
|
1016 |
-
|
1017 |
-
|
1018 |
-
|
1019 |
-
|
1020 |
-
"cls_token": {
|
1021 |
-
"content": "<|begin_of_sentence|>",
|
1022 |
-
"lstrip": false,
|
1023 |
-
"normalized": false,
|
1024 |
-
"rstrip": false,
|
1025 |
-
"single_word": false
|
1026 |
-
},
|
1027 |
-
"eos_token": {
|
1028 |
-
"content": "</s>",
|
1029 |
-
"lstrip": false,
|
1030 |
-
"normalized": false,
|
1031 |
-
"rstrip": false,
|
1032 |
-
"single_word": false
|
1033 |
-
},
|
1034 |
-
"mask_token": {
|
1035 |
-
"content": "<mask:1>",
|
1036 |
-
"lstrip": false,
|
1037 |
-
"normalized": false,
|
1038 |
-
"rstrip": false,
|
1039 |
-
"single_word": false
|
1040 |
-
},
|
1041 |
-
"pad_token": {
|
1042 |
-
"content": "<unk>",
|
1043 |
-
"lstrip": false,
|
1044 |
-
"normalized": false,
|
1045 |
-
"rstrip": false,
|
1046 |
-
"single_word": false
|
1047 |
-
},
|
1048 |
-
"sep_token": {
|
1049 |
-
"content": "<|end_of_sentence|>",
|
1050 |
-
"lstrip": false,
|
1051 |
-
"normalized": false,
|
1052 |
-
"rstrip": false,
|
1053 |
-
"single_word": false
|
1054 |
-
},
|
1055 |
-
"unk_token": {
|
1056 |
-
"content": "<unk>",
|
1057 |
-
"lstrip": false,
|
1058 |
-
"normalized": false,
|
1059 |
-
"rstrip": false,
|
1060 |
-
"single_word": false
|
1061 |
-
}
|
1062 |
}
|
|
|
1010 |
"<|CROP_ROW_SEP|>",
|
1011 |
"<|IMAGE_SEP|>"
|
1012 |
],
|
1013 |
+
"bos_token": "<s>",
|
1014 |
+
"cls_token": "<|begin_of_sentence|>",
|
1015 |
+
"eos_token": "</s>",
|
1016 |
+
"mask_token": "<mask:1>",
|
1017 |
+
"pad_token": "<unk>",
|
1018 |
+
"sep_token": "<|end_of_sentence|>",
|
1019 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1020 |
}
|
test/added_tokens.json
ADDED
@@ -0,0 +1,1011 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|AUDIO_PLACEHOLDER|>": 100296,
|
3 |
+
"<|CROP_COL_SEP|>": 101301,
|
4 |
+
"<|CROP_ROW_SEP|>": 101302,
|
5 |
+
"<|IMAGE_PLACEHOLDER|>": 100295,
|
6 |
+
"<|IMAGE_SEP|>": 101303,
|
7 |
+
"<|LOC_0|>": 100297,
|
8 |
+
"<|LOC_1000|>": 101297,
|
9 |
+
"<|LOC_100|>": 100397,
|
10 |
+
"<|LOC_101|>": 100398,
|
11 |
+
"<|LOC_102|>": 100399,
|
12 |
+
"<|LOC_103|>": 100400,
|
13 |
+
"<|LOC_104|>": 100401,
|
14 |
+
"<|LOC_105|>": 100402,
|
15 |
+
"<|LOC_106|>": 100403,
|
16 |
+
"<|LOC_107|>": 100404,
|
17 |
+
"<|LOC_108|>": 100405,
|
18 |
+
"<|LOC_109|>": 100406,
|
19 |
+
"<|LOC_10|>": 100307,
|
20 |
+
"<|LOC_110|>": 100407,
|
21 |
+
"<|LOC_111|>": 100408,
|
22 |
+
"<|LOC_112|>": 100409,
|
23 |
+
"<|LOC_113|>": 100410,
|
24 |
+
"<|LOC_114|>": 100411,
|
25 |
+
"<|LOC_115|>": 100412,
|
26 |
+
"<|LOC_116|>": 100413,
|
27 |
+
"<|LOC_117|>": 100414,
|
28 |
+
"<|LOC_118|>": 100415,
|
29 |
+
"<|LOC_119|>": 100416,
|
30 |
+
"<|LOC_11|>": 100308,
|
31 |
+
"<|LOC_120|>": 100417,
|
32 |
+
"<|LOC_121|>": 100418,
|
33 |
+
"<|LOC_122|>": 100419,
|
34 |
+
"<|LOC_123|>": 100420,
|
35 |
+
"<|LOC_124|>": 100421,
|
36 |
+
"<|LOC_125|>": 100422,
|
37 |
+
"<|LOC_126|>": 100423,
|
38 |
+
"<|LOC_127|>": 100424,
|
39 |
+
"<|LOC_128|>": 100425,
|
40 |
+
"<|LOC_129|>": 100426,
|
41 |
+
"<|LOC_12|>": 100309,
|
42 |
+
"<|LOC_130|>": 100427,
|
43 |
+
"<|LOC_131|>": 100428,
|
44 |
+
"<|LOC_132|>": 100429,
|
45 |
+
"<|LOC_133|>": 100430,
|
46 |
+
"<|LOC_134|>": 100431,
|
47 |
+
"<|LOC_135|>": 100432,
|
48 |
+
"<|LOC_136|>": 100433,
|
49 |
+
"<|LOC_137|>": 100434,
|
50 |
+
"<|LOC_138|>": 100435,
|
51 |
+
"<|LOC_139|>": 100436,
|
52 |
+
"<|LOC_13|>": 100310,
|
53 |
+
"<|LOC_140|>": 100437,
|
54 |
+
"<|LOC_141|>": 100438,
|
55 |
+
"<|LOC_142|>": 100439,
|
56 |
+
"<|LOC_143|>": 100440,
|
57 |
+
"<|LOC_144|>": 100441,
|
58 |
+
"<|LOC_145|>": 100442,
|
59 |
+
"<|LOC_146|>": 100443,
|
60 |
+
"<|LOC_147|>": 100444,
|
61 |
+
"<|LOC_148|>": 100445,
|
62 |
+
"<|LOC_149|>": 100446,
|
63 |
+
"<|LOC_14|>": 100311,
|
64 |
+
"<|LOC_150|>": 100447,
|
65 |
+
"<|LOC_151|>": 100448,
|
66 |
+
"<|LOC_152|>": 100449,
|
67 |
+
"<|LOC_153|>": 100450,
|
68 |
+
"<|LOC_154|>": 100451,
|
69 |
+
"<|LOC_155|>": 100452,
|
70 |
+
"<|LOC_156|>": 100453,
|
71 |
+
"<|LOC_157|>": 100454,
|
72 |
+
"<|LOC_158|>": 100455,
|
73 |
+
"<|LOC_159|>": 100456,
|
74 |
+
"<|LOC_15|>": 100312,
|
75 |
+
"<|LOC_160|>": 100457,
|
76 |
+
"<|LOC_161|>": 100458,
|
77 |
+
"<|LOC_162|>": 100459,
|
78 |
+
"<|LOC_163|>": 100460,
|
79 |
+
"<|LOC_164|>": 100461,
|
80 |
+
"<|LOC_165|>": 100462,
|
81 |
+
"<|LOC_166|>": 100463,
|
82 |
+
"<|LOC_167|>": 100464,
|
83 |
+
"<|LOC_168|>": 100465,
|
84 |
+
"<|LOC_169|>": 100466,
|
85 |
+
"<|LOC_16|>": 100313,
|
86 |
+
"<|LOC_170|>": 100467,
|
87 |
+
"<|LOC_171|>": 100468,
|
88 |
+
"<|LOC_172|>": 100469,
|
89 |
+
"<|LOC_173|>": 100470,
|
90 |
+
"<|LOC_174|>": 100471,
|
91 |
+
"<|LOC_175|>": 100472,
|
92 |
+
"<|LOC_176|>": 100473,
|
93 |
+
"<|LOC_177|>": 100474,
|
94 |
+
"<|LOC_178|>": 100475,
|
95 |
+
"<|LOC_179|>": 100476,
|
96 |
+
"<|LOC_17|>": 100314,
|
97 |
+
"<|LOC_180|>": 100477,
|
98 |
+
"<|LOC_181|>": 100478,
|
99 |
+
"<|LOC_182|>": 100479,
|
100 |
+
"<|LOC_183|>": 100480,
|
101 |
+
"<|LOC_184|>": 100481,
|
102 |
+
"<|LOC_185|>": 100482,
|
103 |
+
"<|LOC_186|>": 100483,
|
104 |
+
"<|LOC_187|>": 100484,
|
105 |
+
"<|LOC_188|>": 100485,
|
106 |
+
"<|LOC_189|>": 100486,
|
107 |
+
"<|LOC_18|>": 100315,
|
108 |
+
"<|LOC_190|>": 100487,
|
109 |
+
"<|LOC_191|>": 100488,
|
110 |
+
"<|LOC_192|>": 100489,
|
111 |
+
"<|LOC_193|>": 100490,
|
112 |
+
"<|LOC_194|>": 100491,
|
113 |
+
"<|LOC_195|>": 100492,
|
114 |
+
"<|LOC_196|>": 100493,
|
115 |
+
"<|LOC_197|>": 100494,
|
116 |
+
"<|LOC_198|>": 100495,
|
117 |
+
"<|LOC_199|>": 100496,
|
118 |
+
"<|LOC_19|>": 100316,
|
119 |
+
"<|LOC_1|>": 100298,
|
120 |
+
"<|LOC_200|>": 100497,
|
121 |
+
"<|LOC_201|>": 100498,
|
122 |
+
"<|LOC_202|>": 100499,
|
123 |
+
"<|LOC_203|>": 100500,
|
124 |
+
"<|LOC_204|>": 100501,
|
125 |
+
"<|LOC_205|>": 100502,
|
126 |
+
"<|LOC_206|>": 100503,
|
127 |
+
"<|LOC_207|>": 100504,
|
128 |
+
"<|LOC_208|>": 100505,
|
129 |
+
"<|LOC_209|>": 100506,
|
130 |
+
"<|LOC_20|>": 100317,
|
131 |
+
"<|LOC_210|>": 100507,
|
132 |
+
"<|LOC_211|>": 100508,
|
133 |
+
"<|LOC_212|>": 100509,
|
134 |
+
"<|LOC_213|>": 100510,
|
135 |
+
"<|LOC_214|>": 100511,
|
136 |
+
"<|LOC_215|>": 100512,
|
137 |
+
"<|LOC_216|>": 100513,
|
138 |
+
"<|LOC_217|>": 100514,
|
139 |
+
"<|LOC_218|>": 100515,
|
140 |
+
"<|LOC_219|>": 100516,
|
141 |
+
"<|LOC_21|>": 100318,
|
142 |
+
"<|LOC_220|>": 100517,
|
143 |
+
"<|LOC_221|>": 100518,
|
144 |
+
"<|LOC_222|>": 100519,
|
145 |
+
"<|LOC_223|>": 100520,
|
146 |
+
"<|LOC_224|>": 100521,
|
147 |
+
"<|LOC_225|>": 100522,
|
148 |
+
"<|LOC_226|>": 100523,
|
149 |
+
"<|LOC_227|>": 100524,
|
150 |
+
"<|LOC_228|>": 100525,
|
151 |
+
"<|LOC_229|>": 100526,
|
152 |
+
"<|LOC_22|>": 100319,
|
153 |
+
"<|LOC_230|>": 100527,
|
154 |
+
"<|LOC_231|>": 100528,
|
155 |
+
"<|LOC_232|>": 100529,
|
156 |
+
"<|LOC_233|>": 100530,
|
157 |
+
"<|LOC_234|>": 100531,
|
158 |
+
"<|LOC_235|>": 100532,
|
159 |
+
"<|LOC_236|>": 100533,
|
160 |
+
"<|LOC_237|>": 100534,
|
161 |
+
"<|LOC_238|>": 100535,
|
162 |
+
"<|LOC_239|>": 100536,
|
163 |
+
"<|LOC_23|>": 100320,
|
164 |
+
"<|LOC_240|>": 100537,
|
165 |
+
"<|LOC_241|>": 100538,
|
166 |
+
"<|LOC_242|>": 100539,
|
167 |
+
"<|LOC_243|>": 100540,
|
168 |
+
"<|LOC_244|>": 100541,
|
169 |
+
"<|LOC_245|>": 100542,
|
170 |
+
"<|LOC_246|>": 100543,
|
171 |
+
"<|LOC_247|>": 100544,
|
172 |
+
"<|LOC_248|>": 100545,
|
173 |
+
"<|LOC_249|>": 100546,
|
174 |
+
"<|LOC_24|>": 100321,
|
175 |
+
"<|LOC_250|>": 100547,
|
176 |
+
"<|LOC_251|>": 100548,
|
177 |
+
"<|LOC_252|>": 100549,
|
178 |
+
"<|LOC_253|>": 100550,
|
179 |
+
"<|LOC_254|>": 100551,
|
180 |
+
"<|LOC_255|>": 100552,
|
181 |
+
"<|LOC_256|>": 100553,
|
182 |
+
"<|LOC_257|>": 100554,
|
183 |
+
"<|LOC_258|>": 100555,
|
184 |
+
"<|LOC_259|>": 100556,
|
185 |
+
"<|LOC_25|>": 100322,
|
186 |
+
"<|LOC_260|>": 100557,
|
187 |
+
"<|LOC_261|>": 100558,
|
188 |
+
"<|LOC_262|>": 100559,
|
189 |
+
"<|LOC_263|>": 100560,
|
190 |
+
"<|LOC_264|>": 100561,
|
191 |
+
"<|LOC_265|>": 100562,
|
192 |
+
"<|LOC_266|>": 100563,
|
193 |
+
"<|LOC_267|>": 100564,
|
194 |
+
"<|LOC_268|>": 100565,
|
195 |
+
"<|LOC_269|>": 100566,
|
196 |
+
"<|LOC_26|>": 100323,
|
197 |
+
"<|LOC_270|>": 100567,
|
198 |
+
"<|LOC_271|>": 100568,
|
199 |
+
"<|LOC_272|>": 100569,
|
200 |
+
"<|LOC_273|>": 100570,
|
201 |
+
"<|LOC_274|>": 100571,
|
202 |
+
"<|LOC_275|>": 100572,
|
203 |
+
"<|LOC_276|>": 100573,
|
204 |
+
"<|LOC_277|>": 100574,
|
205 |
+
"<|LOC_278|>": 100575,
|
206 |
+
"<|LOC_279|>": 100576,
|
207 |
+
"<|LOC_27|>": 100324,
|
208 |
+
"<|LOC_280|>": 100577,
|
209 |
+
"<|LOC_281|>": 100578,
|
210 |
+
"<|LOC_282|>": 100579,
|
211 |
+
"<|LOC_283|>": 100580,
|
212 |
+
"<|LOC_284|>": 100581,
|
213 |
+
"<|LOC_285|>": 100582,
|
214 |
+
"<|LOC_286|>": 100583,
|
215 |
+
"<|LOC_287|>": 100584,
|
216 |
+
"<|LOC_288|>": 100585,
|
217 |
+
"<|LOC_289|>": 100586,
|
218 |
+
"<|LOC_28|>": 100325,
|
219 |
+
"<|LOC_290|>": 100587,
|
220 |
+
"<|LOC_291|>": 100588,
|
221 |
+
"<|LOC_292|>": 100589,
|
222 |
+
"<|LOC_293|>": 100590,
|
223 |
+
"<|LOC_294|>": 100591,
|
224 |
+
"<|LOC_295|>": 100592,
|
225 |
+
"<|LOC_296|>": 100593,
|
226 |
+
"<|LOC_297|>": 100594,
|
227 |
+
"<|LOC_298|>": 100595,
|
228 |
+
"<|LOC_299|>": 100596,
|
229 |
+
"<|LOC_29|>": 100326,
|
230 |
+
"<|LOC_2|>": 100299,
|
231 |
+
"<|LOC_300|>": 100597,
|
232 |
+
"<|LOC_301|>": 100598,
|
233 |
+
"<|LOC_302|>": 100599,
|
234 |
+
"<|LOC_303|>": 100600,
|
235 |
+
"<|LOC_304|>": 100601,
|
236 |
+
"<|LOC_305|>": 100602,
|
237 |
+
"<|LOC_306|>": 100603,
|
238 |
+
"<|LOC_307|>": 100604,
|
239 |
+
"<|LOC_308|>": 100605,
|
240 |
+
"<|LOC_309|>": 100606,
|
241 |
+
"<|LOC_30|>": 100327,
|
242 |
+
"<|LOC_310|>": 100607,
|
243 |
+
"<|LOC_311|>": 100608,
|
244 |
+
"<|LOC_312|>": 100609,
|
245 |
+
"<|LOC_313|>": 100610,
|
246 |
+
"<|LOC_314|>": 100611,
|
247 |
+
"<|LOC_315|>": 100612,
|
248 |
+
"<|LOC_316|>": 100613,
|
249 |
+
"<|LOC_317|>": 100614,
|
250 |
+
"<|LOC_318|>": 100615,
|
251 |
+
"<|LOC_319|>": 100616,
|
252 |
+
"<|LOC_31|>": 100328,
|
253 |
+
"<|LOC_320|>": 100617,
|
254 |
+
"<|LOC_321|>": 100618,
|
255 |
+
"<|LOC_322|>": 100619,
|
256 |
+
"<|LOC_323|>": 100620,
|
257 |
+
"<|LOC_324|>": 100621,
|
258 |
+
"<|LOC_325|>": 100622,
|
259 |
+
"<|LOC_326|>": 100623,
|
260 |
+
"<|LOC_327|>": 100624,
|
261 |
+
"<|LOC_328|>": 100625,
|
262 |
+
"<|LOC_329|>": 100626,
|
263 |
+
"<|LOC_32|>": 100329,
|
264 |
+
"<|LOC_330|>": 100627,
|
265 |
+
"<|LOC_331|>": 100628,
|
266 |
+
"<|LOC_332|>": 100629,
|
267 |
+
"<|LOC_333|>": 100630,
|
268 |
+
"<|LOC_334|>": 100631,
|
269 |
+
"<|LOC_335|>": 100632,
|
270 |
+
"<|LOC_336|>": 100633,
|
271 |
+
"<|LOC_337|>": 100634,
|
272 |
+
"<|LOC_338|>": 100635,
|
273 |
+
"<|LOC_339|>": 100636,
|
274 |
+
"<|LOC_33|>": 100330,
|
275 |
+
"<|LOC_340|>": 100637,
|
276 |
+
"<|LOC_341|>": 100638,
|
277 |
+
"<|LOC_342|>": 100639,
|
278 |
+
"<|LOC_343|>": 100640,
|
279 |
+
"<|LOC_344|>": 100641,
|
280 |
+
"<|LOC_345|>": 100642,
|
281 |
+
"<|LOC_346|>": 100643,
|
282 |
+
"<|LOC_347|>": 100644,
|
283 |
+
"<|LOC_348|>": 100645,
|
284 |
+
"<|LOC_349|>": 100646,
|
285 |
+
"<|LOC_34|>": 100331,
|
286 |
+
"<|LOC_350|>": 100647,
|
287 |
+
"<|LOC_351|>": 100648,
|
288 |
+
"<|LOC_352|>": 100649,
|
289 |
+
"<|LOC_353|>": 100650,
|
290 |
+
"<|LOC_354|>": 100651,
|
291 |
+
"<|LOC_355|>": 100652,
|
292 |
+
"<|LOC_356|>": 100653,
|
293 |
+
"<|LOC_357|>": 100654,
|
294 |
+
"<|LOC_358|>": 100655,
|
295 |
+
"<|LOC_359|>": 100656,
|
296 |
+
"<|LOC_35|>": 100332,
|
297 |
+
"<|LOC_360|>": 100657,
|
298 |
+
"<|LOC_361|>": 100658,
|
299 |
+
"<|LOC_362|>": 100659,
|
300 |
+
"<|LOC_363|>": 100660,
|
301 |
+
"<|LOC_364|>": 100661,
|
302 |
+
"<|LOC_365|>": 100662,
|
303 |
+
"<|LOC_366|>": 100663,
|
304 |
+
"<|LOC_367|>": 100664,
|
305 |
+
"<|LOC_368|>": 100665,
|
306 |
+
"<|LOC_369|>": 100666,
|
307 |
+
"<|LOC_36|>": 100333,
|
308 |
+
"<|LOC_370|>": 100667,
|
309 |
+
"<|LOC_371|>": 100668,
|
310 |
+
"<|LOC_372|>": 100669,
|
311 |
+
"<|LOC_373|>": 100670,
|
312 |
+
"<|LOC_374|>": 100671,
|
313 |
+
"<|LOC_375|>": 100672,
|
314 |
+
"<|LOC_376|>": 100673,
|
315 |
+
"<|LOC_377|>": 100674,
|
316 |
+
"<|LOC_378|>": 100675,
|
317 |
+
"<|LOC_379|>": 100676,
|
318 |
+
"<|LOC_37|>": 100334,
|
319 |
+
"<|LOC_380|>": 100677,
|
320 |
+
"<|LOC_381|>": 100678,
|
321 |
+
"<|LOC_382|>": 100679,
|
322 |
+
"<|LOC_383|>": 100680,
|
323 |
+
"<|LOC_384|>": 100681,
|
324 |
+
"<|LOC_385|>": 100682,
|
325 |
+
"<|LOC_386|>": 100683,
|
326 |
+
"<|LOC_387|>": 100684,
|
327 |
+
"<|LOC_388|>": 100685,
|
328 |
+
"<|LOC_389|>": 100686,
|
329 |
+
"<|LOC_38|>": 100335,
|
330 |
+
"<|LOC_390|>": 100687,
|
331 |
+
"<|LOC_391|>": 100688,
|
332 |
+
"<|LOC_392|>": 100689,
|
333 |
+
"<|LOC_393|>": 100690,
|
334 |
+
"<|LOC_394|>": 100691,
|
335 |
+
"<|LOC_395|>": 100692,
|
336 |
+
"<|LOC_396|>": 100693,
|
337 |
+
"<|LOC_397|>": 100694,
|
338 |
+
"<|LOC_398|>": 100695,
|
339 |
+
"<|LOC_399|>": 100696,
|
340 |
+
"<|LOC_39|>": 100336,
|
341 |
+
"<|LOC_3|>": 100300,
|
342 |
+
"<|LOC_400|>": 100697,
|
343 |
+
"<|LOC_401|>": 100698,
|
344 |
+
"<|LOC_402|>": 100699,
|
345 |
+
"<|LOC_403|>": 100700,
|
346 |
+
"<|LOC_404|>": 100701,
|
347 |
+
"<|LOC_405|>": 100702,
|
348 |
+
"<|LOC_406|>": 100703,
|
349 |
+
"<|LOC_407|>": 100704,
|
350 |
+
"<|LOC_408|>": 100705,
|
351 |
+
"<|LOC_409|>": 100706,
|
352 |
+
"<|LOC_40|>": 100337,
|
353 |
+
"<|LOC_410|>": 100707,
|
354 |
+
"<|LOC_411|>": 100708,
|
355 |
+
"<|LOC_412|>": 100709,
|
356 |
+
"<|LOC_413|>": 100710,
|
357 |
+
"<|LOC_414|>": 100711,
|
358 |
+
"<|LOC_415|>": 100712,
|
359 |
+
"<|LOC_416|>": 100713,
|
360 |
+
"<|LOC_417|>": 100714,
|
361 |
+
"<|LOC_418|>": 100715,
|
362 |
+
"<|LOC_419|>": 100716,
|
363 |
+
"<|LOC_41|>": 100338,
|
364 |
+
"<|LOC_420|>": 100717,
|
365 |
+
"<|LOC_421|>": 100718,
|
366 |
+
"<|LOC_422|>": 100719,
|
367 |
+
"<|LOC_423|>": 100720,
|
368 |
+
"<|LOC_424|>": 100721,
|
369 |
+
"<|LOC_425|>": 100722,
|
370 |
+
"<|LOC_426|>": 100723,
|
371 |
+
"<|LOC_427|>": 100724,
|
372 |
+
"<|LOC_428|>": 100725,
|
373 |
+
"<|LOC_429|>": 100726,
|
374 |
+
"<|LOC_42|>": 100339,
|
375 |
+
"<|LOC_430|>": 100727,
|
376 |
+
"<|LOC_431|>": 100728,
|
377 |
+
"<|LOC_432|>": 100729,
|
378 |
+
"<|LOC_433|>": 100730,
|
379 |
+
"<|LOC_434|>": 100731,
|
380 |
+
"<|LOC_435|>": 100732,
|
381 |
+
"<|LOC_436|>": 100733,
|
382 |
+
"<|LOC_437|>": 100734,
|
383 |
+
"<|LOC_438|>": 100735,
|
384 |
+
"<|LOC_439|>": 100736,
|
385 |
+
"<|LOC_43|>": 100340,
|
386 |
+
"<|LOC_440|>": 100737,
|
387 |
+
"<|LOC_441|>": 100738,
|
388 |
+
"<|LOC_442|>": 100739,
|
389 |
+
"<|LOC_443|>": 100740,
|
390 |
+
"<|LOC_444|>": 100741,
|
391 |
+
"<|LOC_445|>": 100742,
|
392 |
+
"<|LOC_446|>": 100743,
|
393 |
+
"<|LOC_447|>": 100744,
|
394 |
+
"<|LOC_448|>": 100745,
|
395 |
+
"<|LOC_449|>": 100746,
|
396 |
+
"<|LOC_44|>": 100341,
|
397 |
+
"<|LOC_450|>": 100747,
|
398 |
+
"<|LOC_451|>": 100748,
|
399 |
+
"<|LOC_452|>": 100749,
|
400 |
+
"<|LOC_453|>": 100750,
|
401 |
+
"<|LOC_454|>": 100751,
|
402 |
+
"<|LOC_455|>": 100752,
|
403 |
+
"<|LOC_456|>": 100753,
|
404 |
+
"<|LOC_457|>": 100754,
|
405 |
+
"<|LOC_458|>": 100755,
|
406 |
+
"<|LOC_459|>": 100756,
|
407 |
+
"<|LOC_45|>": 100342,
|
408 |
+
"<|LOC_460|>": 100757,
|
409 |
+
"<|LOC_461|>": 100758,
|
410 |
+
"<|LOC_462|>": 100759,
|
411 |
+
"<|LOC_463|>": 100760,
|
412 |
+
"<|LOC_464|>": 100761,
|
413 |
+
"<|LOC_465|>": 100762,
|
414 |
+
"<|LOC_466|>": 100763,
|
415 |
+
"<|LOC_467|>": 100764,
|
416 |
+
"<|LOC_468|>": 100765,
|
417 |
+
"<|LOC_469|>": 100766,
|
418 |
+
"<|LOC_46|>": 100343,
|
419 |
+
"<|LOC_470|>": 100767,
|
420 |
+
"<|LOC_471|>": 100768,
|
421 |
+
"<|LOC_472|>": 100769,
|
422 |
+
"<|LOC_473|>": 100770,
|
423 |
+
"<|LOC_474|>": 100771,
|
424 |
+
"<|LOC_475|>": 100772,
|
425 |
+
"<|LOC_476|>": 100773,
|
426 |
+
"<|LOC_477|>": 100774,
|
427 |
+
"<|LOC_478|>": 100775,
|
428 |
+
"<|LOC_479|>": 100776,
|
429 |
+
"<|LOC_47|>": 100344,
|
430 |
+
"<|LOC_480|>": 100777,
|
431 |
+
"<|LOC_481|>": 100778,
|
432 |
+
"<|LOC_482|>": 100779,
|
433 |
+
"<|LOC_483|>": 100780,
|
434 |
+
"<|LOC_484|>": 100781,
|
435 |
+
"<|LOC_485|>": 100782,
|
436 |
+
"<|LOC_486|>": 100783,
|
437 |
+
"<|LOC_487|>": 100784,
|
438 |
+
"<|LOC_488|>": 100785,
|
439 |
+
"<|LOC_489|>": 100786,
|
440 |
+
"<|LOC_48|>": 100345,
|
441 |
+
"<|LOC_490|>": 100787,
|
442 |
+
"<|LOC_491|>": 100788,
|
443 |
+
"<|LOC_492|>": 100789,
|
444 |
+
"<|LOC_493|>": 100790,
|
445 |
+
"<|LOC_494|>": 100791,
|
446 |
+
"<|LOC_495|>": 100792,
|
447 |
+
"<|LOC_496|>": 100793,
|
448 |
+
"<|LOC_497|>": 100794,
|
449 |
+
"<|LOC_498|>": 100795,
|
450 |
+
"<|LOC_499|>": 100796,
|
451 |
+
"<|LOC_49|>": 100346,
|
452 |
+
"<|LOC_4|>": 100301,
|
453 |
+
"<|LOC_500|>": 100797,
|
454 |
+
"<|LOC_501|>": 100798,
|
455 |
+
"<|LOC_502|>": 100799,
|
456 |
+
"<|LOC_503|>": 100800,
|
457 |
+
"<|LOC_504|>": 100801,
|
458 |
+
"<|LOC_505|>": 100802,
|
459 |
+
"<|LOC_506|>": 100803,
|
460 |
+
"<|LOC_507|>": 100804,
|
461 |
+
"<|LOC_508|>": 100805,
|
462 |
+
"<|LOC_509|>": 100806,
|
463 |
+
"<|LOC_50|>": 100347,
|
464 |
+
"<|LOC_510|>": 100807,
|
465 |
+
"<|LOC_511|>": 100808,
|
466 |
+
"<|LOC_512|>": 100809,
|
467 |
+
"<|LOC_513|>": 100810,
|
468 |
+
"<|LOC_514|>": 100811,
|
469 |
+
"<|LOC_515|>": 100812,
|
470 |
+
"<|LOC_516|>": 100813,
|
471 |
+
"<|LOC_517|>": 100814,
|
472 |
+
"<|LOC_518|>": 100815,
|
473 |
+
"<|LOC_519|>": 100816,
|
474 |
+
"<|LOC_51|>": 100348,
|
475 |
+
"<|LOC_520|>": 100817,
|
476 |
+
"<|LOC_521|>": 100818,
|
477 |
+
"<|LOC_522|>": 100819,
|
478 |
+
"<|LOC_523|>": 100820,
|
479 |
+
"<|LOC_524|>": 100821,
|
480 |
+
"<|LOC_525|>": 100822,
|
481 |
+
"<|LOC_526|>": 100823,
|
482 |
+
"<|LOC_527|>": 100824,
|
483 |
+
"<|LOC_528|>": 100825,
|
484 |
+
"<|LOC_529|>": 100826,
|
485 |
+
"<|LOC_52|>": 100349,
|
486 |
+
"<|LOC_530|>": 100827,
|
487 |
+
"<|LOC_531|>": 100828,
|
488 |
+
"<|LOC_532|>": 100829,
|
489 |
+
"<|LOC_533|>": 100830,
|
490 |
+
"<|LOC_534|>": 100831,
|
491 |
+
"<|LOC_535|>": 100832,
|
492 |
+
"<|LOC_536|>": 100833,
|
493 |
+
"<|LOC_537|>": 100834,
|
494 |
+
"<|LOC_538|>": 100835,
|
495 |
+
"<|LOC_539|>": 100836,
|
496 |
+
"<|LOC_53|>": 100350,
|
497 |
+
"<|LOC_540|>": 100837,
|
498 |
+
"<|LOC_541|>": 100838,
|
499 |
+
"<|LOC_542|>": 100839,
|
500 |
+
"<|LOC_543|>": 100840,
|
501 |
+
"<|LOC_544|>": 100841,
|
502 |
+
"<|LOC_545|>": 100842,
|
503 |
+
"<|LOC_546|>": 100843,
|
504 |
+
"<|LOC_547|>": 100844,
|
505 |
+
"<|LOC_548|>": 100845,
|
506 |
+
"<|LOC_549|>": 100846,
|
507 |
+
"<|LOC_54|>": 100351,
|
508 |
+
"<|LOC_550|>": 100847,
|
509 |
+
"<|LOC_551|>": 100848,
|
510 |
+
"<|LOC_552|>": 100849,
|
511 |
+
"<|LOC_553|>": 100850,
|
512 |
+
"<|LOC_554|>": 100851,
|
513 |
+
"<|LOC_555|>": 100852,
|
514 |
+
"<|LOC_556|>": 100853,
|
515 |
+
"<|LOC_557|>": 100854,
|
516 |
+
"<|LOC_558|>": 100855,
|
517 |
+
"<|LOC_559|>": 100856,
|
518 |
+
"<|LOC_55|>": 100352,
|
519 |
+
"<|LOC_560|>": 100857,
|
520 |
+
"<|LOC_561|>": 100858,
|
521 |
+
"<|LOC_562|>": 100859,
|
522 |
+
"<|LOC_563|>": 100860,
|
523 |
+
"<|LOC_564|>": 100861,
|
524 |
+
"<|LOC_565|>": 100862,
|
525 |
+
"<|LOC_566|>": 100863,
|
526 |
+
"<|LOC_567|>": 100864,
|
527 |
+
"<|LOC_568|>": 100865,
|
528 |
+
"<|LOC_569|>": 100866,
|
529 |
+
"<|LOC_56|>": 100353,
|
530 |
+
"<|LOC_570|>": 100867,
|
531 |
+
"<|LOC_571|>": 100868,
|
532 |
+
"<|LOC_572|>": 100869,
|
533 |
+
"<|LOC_573|>": 100870,
|
534 |
+
"<|LOC_574|>": 100871,
|
535 |
+
"<|LOC_575|>": 100872,
|
536 |
+
"<|LOC_576|>": 100873,
|
537 |
+
"<|LOC_577|>": 100874,
|
538 |
+
"<|LOC_578|>": 100875,
|
539 |
+
"<|LOC_579|>": 100876,
|
540 |
+
"<|LOC_57|>": 100354,
|
541 |
+
"<|LOC_580|>": 100877,
|
542 |
+
"<|LOC_581|>": 100878,
|
543 |
+
"<|LOC_582|>": 100879,
|
544 |
+
"<|LOC_583|>": 100880,
|
545 |
+
"<|LOC_584|>": 100881,
|
546 |
+
"<|LOC_585|>": 100882,
|
547 |
+
"<|LOC_586|>": 100883,
|
548 |
+
"<|LOC_587|>": 100884,
|
549 |
+
"<|LOC_588|>": 100885,
|
550 |
+
"<|LOC_589|>": 100886,
|
551 |
+
"<|LOC_58|>": 100355,
|
552 |
+
"<|LOC_590|>": 100887,
|
553 |
+
"<|LOC_591|>": 100888,
|
554 |
+
"<|LOC_592|>": 100889,
|
555 |
+
"<|LOC_593|>": 100890,
|
556 |
+
"<|LOC_594|>": 100891,
|
557 |
+
"<|LOC_595|>": 100892,
|
558 |
+
"<|LOC_596|>": 100893,
|
559 |
+
"<|LOC_597|>": 100894,
|
560 |
+
"<|LOC_598|>": 100895,
|
561 |
+
"<|LOC_599|>": 100896,
|
562 |
+
"<|LOC_59|>": 100356,
|
563 |
+
"<|LOC_5|>": 100302,
|
564 |
+
"<|LOC_600|>": 100897,
|
565 |
+
"<|LOC_601|>": 100898,
|
566 |
+
"<|LOC_602|>": 100899,
|
567 |
+
"<|LOC_603|>": 100900,
|
568 |
+
"<|LOC_604|>": 100901,
|
569 |
+
"<|LOC_605|>": 100902,
|
570 |
+
"<|LOC_606|>": 100903,
|
571 |
+
"<|LOC_607|>": 100904,
|
572 |
+
"<|LOC_608|>": 100905,
|
573 |
+
"<|LOC_609|>": 100906,
|
574 |
+
"<|LOC_60|>": 100357,
|
575 |
+
"<|LOC_610|>": 100907,
|
576 |
+
"<|LOC_611|>": 100908,
|
577 |
+
"<|LOC_612|>": 100909,
|
578 |
+
"<|LOC_613|>": 100910,
|
579 |
+
"<|LOC_614|>": 100911,
|
580 |
+
"<|LOC_615|>": 100912,
|
581 |
+
"<|LOC_616|>": 100913,
|
582 |
+
"<|LOC_617|>": 100914,
|
583 |
+
"<|LOC_618|>": 100915,
|
584 |
+
"<|LOC_619|>": 100916,
|
585 |
+
"<|LOC_61|>": 100358,
|
586 |
+
"<|LOC_620|>": 100917,
|
587 |
+
"<|LOC_621|>": 100918,
|
588 |
+
"<|LOC_622|>": 100919,
|
589 |
+
"<|LOC_623|>": 100920,
|
590 |
+
"<|LOC_624|>": 100921,
|
591 |
+
"<|LOC_625|>": 100922,
|
592 |
+
"<|LOC_626|>": 100923,
|
593 |
+
"<|LOC_627|>": 100924,
|
594 |
+
"<|LOC_628|>": 100925,
|
595 |
+
"<|LOC_629|>": 100926,
|
596 |
+
"<|LOC_62|>": 100359,
|
597 |
+
"<|LOC_630|>": 100927,
|
598 |
+
"<|LOC_631|>": 100928,
|
599 |
+
"<|LOC_632|>": 100929,
|
600 |
+
"<|LOC_633|>": 100930,
|
601 |
+
"<|LOC_634|>": 100931,
|
602 |
+
"<|LOC_635|>": 100932,
|
603 |
+
"<|LOC_636|>": 100933,
|
604 |
+
"<|LOC_637|>": 100934,
|
605 |
+
"<|LOC_638|>": 100935,
|
606 |
+
"<|LOC_639|>": 100936,
|
607 |
+
"<|LOC_63|>": 100360,
|
608 |
+
"<|LOC_640|>": 100937,
|
609 |
+
"<|LOC_641|>": 100938,
|
610 |
+
"<|LOC_642|>": 100939,
|
611 |
+
"<|LOC_643|>": 100940,
|
612 |
+
"<|LOC_644|>": 100941,
|
613 |
+
"<|LOC_645|>": 100942,
|
614 |
+
"<|LOC_646|>": 100943,
|
615 |
+
"<|LOC_647|>": 100944,
|
616 |
+
"<|LOC_648|>": 100945,
|
617 |
+
"<|LOC_649|>": 100946,
|
618 |
+
"<|LOC_64|>": 100361,
|
619 |
+
"<|LOC_650|>": 100947,
|
620 |
+
"<|LOC_651|>": 100948,
|
621 |
+
"<|LOC_652|>": 100949,
|
622 |
+
"<|LOC_653|>": 100950,
|
623 |
+
"<|LOC_654|>": 100951,
|
624 |
+
"<|LOC_655|>": 100952,
|
625 |
+
"<|LOC_656|>": 100953,
|
626 |
+
"<|LOC_657|>": 100954,
|
627 |
+
"<|LOC_658|>": 100955,
|
628 |
+
"<|LOC_659|>": 100956,
|
629 |
+
"<|LOC_65|>": 100362,
|
630 |
+
"<|LOC_660|>": 100957,
|
631 |
+
"<|LOC_661|>": 100958,
|
632 |
+
"<|LOC_662|>": 100959,
|
633 |
+
"<|LOC_663|>": 100960,
|
634 |
+
"<|LOC_664|>": 100961,
|
635 |
+
"<|LOC_665|>": 100962,
|
636 |
+
"<|LOC_666|>": 100963,
|
637 |
+
"<|LOC_667|>": 100964,
|
638 |
+
"<|LOC_668|>": 100965,
|
639 |
+
"<|LOC_669|>": 100966,
|
640 |
+
"<|LOC_66|>": 100363,
|
641 |
+
"<|LOC_670|>": 100967,
|
642 |
+
"<|LOC_671|>": 100968,
|
643 |
+
"<|LOC_672|>": 100969,
|
644 |
+
"<|LOC_673|>": 100970,
|
645 |
+
"<|LOC_674|>": 100971,
|
646 |
+
"<|LOC_675|>": 100972,
|
647 |
+
"<|LOC_676|>": 100973,
|
648 |
+
"<|LOC_677|>": 100974,
|
649 |
+
"<|LOC_678|>": 100975,
|
650 |
+
"<|LOC_679|>": 100976,
|
651 |
+
"<|LOC_67|>": 100364,
|
652 |
+
"<|LOC_680|>": 100977,
|
653 |
+
"<|LOC_681|>": 100978,
|
654 |
+
"<|LOC_682|>": 100979,
|
655 |
+
"<|LOC_683|>": 100980,
|
656 |
+
"<|LOC_684|>": 100981,
|
657 |
+
"<|LOC_685|>": 100982,
|
658 |
+
"<|LOC_686|>": 100983,
|
659 |
+
"<|LOC_687|>": 100984,
|
660 |
+
"<|LOC_688|>": 100985,
|
661 |
+
"<|LOC_689|>": 100986,
|
662 |
+
"<|LOC_68|>": 100365,
|
663 |
+
"<|LOC_690|>": 100987,
|
664 |
+
"<|LOC_691|>": 100988,
|
665 |
+
"<|LOC_692|>": 100989,
|
666 |
+
"<|LOC_693|>": 100990,
|
667 |
+
"<|LOC_694|>": 100991,
|
668 |
+
"<|LOC_695|>": 100992,
|
669 |
+
"<|LOC_696|>": 100993,
|
670 |
+
"<|LOC_697|>": 100994,
|
671 |
+
"<|LOC_698|>": 100995,
|
672 |
+
"<|LOC_699|>": 100996,
|
673 |
+
"<|LOC_69|>": 100366,
|
674 |
+
"<|LOC_6|>": 100303,
|
675 |
+
"<|LOC_700|>": 100997,
|
676 |
+
"<|LOC_701|>": 100998,
|
677 |
+
"<|LOC_702|>": 100999,
|
678 |
+
"<|LOC_703|>": 101000,
|
679 |
+
"<|LOC_704|>": 101001,
|
680 |
+
"<|LOC_705|>": 101002,
|
681 |
+
"<|LOC_706|>": 101003,
|
682 |
+
"<|LOC_707|>": 101004,
|
683 |
+
"<|LOC_708|>": 101005,
|
684 |
+
"<|LOC_709|>": 101006,
|
685 |
+
"<|LOC_70|>": 100367,
|
686 |
+
"<|LOC_710|>": 101007,
|
687 |
+
"<|LOC_711|>": 101008,
|
688 |
+
"<|LOC_712|>": 101009,
|
689 |
+
"<|LOC_713|>": 101010,
|
690 |
+
"<|LOC_714|>": 101011,
|
691 |
+
"<|LOC_715|>": 101012,
|
692 |
+
"<|LOC_716|>": 101013,
|
693 |
+
"<|LOC_717|>": 101014,
|
694 |
+
"<|LOC_718|>": 101015,
|
695 |
+
"<|LOC_719|>": 101016,
|
696 |
+
"<|LOC_71|>": 100368,
|
697 |
+
"<|LOC_720|>": 101017,
|
698 |
+
"<|LOC_721|>": 101018,
|
699 |
+
"<|LOC_722|>": 101019,
|
700 |
+
"<|LOC_723|>": 101020,
|
701 |
+
"<|LOC_724|>": 101021,
|
702 |
+
"<|LOC_725|>": 101022,
|
703 |
+
"<|LOC_726|>": 101023,
|
704 |
+
"<|LOC_727|>": 101024,
|
705 |
+
"<|LOC_728|>": 101025,
|
706 |
+
"<|LOC_729|>": 101026,
|
707 |
+
"<|LOC_72|>": 100369,
|
708 |
+
"<|LOC_730|>": 101027,
|
709 |
+
"<|LOC_731|>": 101028,
|
710 |
+
"<|LOC_732|>": 101029,
|
711 |
+
"<|LOC_733|>": 101030,
|
712 |
+
"<|LOC_734|>": 101031,
|
713 |
+
"<|LOC_735|>": 101032,
|
714 |
+
"<|LOC_736|>": 101033,
|
715 |
+
"<|LOC_737|>": 101034,
|
716 |
+
"<|LOC_738|>": 101035,
|
717 |
+
"<|LOC_739|>": 101036,
|
718 |
+
"<|LOC_73|>": 100370,
|
719 |
+
"<|LOC_740|>": 101037,
|
720 |
+
"<|LOC_741|>": 101038,
|
721 |
+
"<|LOC_742|>": 101039,
|
722 |
+
"<|LOC_743|>": 101040,
|
723 |
+
"<|LOC_744|>": 101041,
|
724 |
+
"<|LOC_745|>": 101042,
|
725 |
+
"<|LOC_746|>": 101043,
|
726 |
+
"<|LOC_747|>": 101044,
|
727 |
+
"<|LOC_748|>": 101045,
|
728 |
+
"<|LOC_749|>": 101046,
|
729 |
+
"<|LOC_74|>": 100371,
|
730 |
+
"<|LOC_750|>": 101047,
|
731 |
+
"<|LOC_751|>": 101048,
|
732 |
+
"<|LOC_752|>": 101049,
|
733 |
+
"<|LOC_753|>": 101050,
|
734 |
+
"<|LOC_754|>": 101051,
|
735 |
+
"<|LOC_755|>": 101052,
|
736 |
+
"<|LOC_756|>": 101053,
|
737 |
+
"<|LOC_757|>": 101054,
|
738 |
+
"<|LOC_758|>": 101055,
|
739 |
+
"<|LOC_759|>": 101056,
|
740 |
+
"<|LOC_75|>": 100372,
|
741 |
+
"<|LOC_760|>": 101057,
|
742 |
+
"<|LOC_761|>": 101058,
|
743 |
+
"<|LOC_762|>": 101059,
|
744 |
+
"<|LOC_763|>": 101060,
|
745 |
+
"<|LOC_764|>": 101061,
|
746 |
+
"<|LOC_765|>": 101062,
|
747 |
+
"<|LOC_766|>": 101063,
|
748 |
+
"<|LOC_767|>": 101064,
|
749 |
+
"<|LOC_768|>": 101065,
|
750 |
+
"<|LOC_769|>": 101066,
|
751 |
+
"<|LOC_76|>": 100373,
|
752 |
+
"<|LOC_770|>": 101067,
|
753 |
+
"<|LOC_771|>": 101068,
|
754 |
+
"<|LOC_772|>": 101069,
|
755 |
+
"<|LOC_773|>": 101070,
|
756 |
+
"<|LOC_774|>": 101071,
|
757 |
+
"<|LOC_775|>": 101072,
|
758 |
+
"<|LOC_776|>": 101073,
|
759 |
+
"<|LOC_777|>": 101074,
|
760 |
+
"<|LOC_778|>": 101075,
|
761 |
+
"<|LOC_779|>": 101076,
|
762 |
+
"<|LOC_77|>": 100374,
|
763 |
+
"<|LOC_780|>": 101077,
|
764 |
+
"<|LOC_781|>": 101078,
|
765 |
+
"<|LOC_782|>": 101079,
|
766 |
+
"<|LOC_783|>": 101080,
|
767 |
+
"<|LOC_784|>": 101081,
|
768 |
+
"<|LOC_785|>": 101082,
|
769 |
+
"<|LOC_786|>": 101083,
|
770 |
+
"<|LOC_787|>": 101084,
|
771 |
+
"<|LOC_788|>": 101085,
|
772 |
+
"<|LOC_789|>": 101086,
|
773 |
+
"<|LOC_78|>": 100375,
|
774 |
+
"<|LOC_790|>": 101087,
|
775 |
+
"<|LOC_791|>": 101088,
|
776 |
+
"<|LOC_792|>": 101089,
|
777 |
+
"<|LOC_793|>": 101090,
|
778 |
+
"<|LOC_794|>": 101091,
|
779 |
+
"<|LOC_795|>": 101092,
|
780 |
+
"<|LOC_796|>": 101093,
|
781 |
+
"<|LOC_797|>": 101094,
|
782 |
+
"<|LOC_798|>": 101095,
|
783 |
+
"<|LOC_799|>": 101096,
|
784 |
+
"<|LOC_79|>": 100376,
|
785 |
+
"<|LOC_7|>": 100304,
|
786 |
+
"<|LOC_800|>": 101097,
|
787 |
+
"<|LOC_801|>": 101098,
|
788 |
+
"<|LOC_802|>": 101099,
|
789 |
+
"<|LOC_803|>": 101100,
|
790 |
+
"<|LOC_804|>": 101101,
|
791 |
+
"<|LOC_805|>": 101102,
|
792 |
+
"<|LOC_806|>": 101103,
|
793 |
+
"<|LOC_807|>": 101104,
|
794 |
+
"<|LOC_808|>": 101105,
|
795 |
+
"<|LOC_809|>": 101106,
|
796 |
+
"<|LOC_80|>": 100377,
|
797 |
+
"<|LOC_810|>": 101107,
|
798 |
+
"<|LOC_811|>": 101108,
|
799 |
+
"<|LOC_812|>": 101109,
|
800 |
+
"<|LOC_813|>": 101110,
|
801 |
+
"<|LOC_814|>": 101111,
|
802 |
+
"<|LOC_815|>": 101112,
|
803 |
+
"<|LOC_816|>": 101113,
|
804 |
+
"<|LOC_817|>": 101114,
|
805 |
+
"<|LOC_818|>": 101115,
|
806 |
+
"<|LOC_819|>": 101116,
|
807 |
+
"<|LOC_81|>": 100378,
|
808 |
+
"<|LOC_820|>": 101117,
|
809 |
+
"<|LOC_821|>": 101118,
|
810 |
+
"<|LOC_822|>": 101119,
|
811 |
+
"<|LOC_823|>": 101120,
|
812 |
+
"<|LOC_824|>": 101121,
|
813 |
+
"<|LOC_825|>": 101122,
|
814 |
+
"<|LOC_826|>": 101123,
|
815 |
+
"<|LOC_827|>": 101124,
|
816 |
+
"<|LOC_828|>": 101125,
|
817 |
+
"<|LOC_829|>": 101126,
|
818 |
+
"<|LOC_82|>": 100379,
|
819 |
+
"<|LOC_830|>": 101127,
|
820 |
+
"<|LOC_831|>": 101128,
|
821 |
+
"<|LOC_832|>": 101129,
|
822 |
+
"<|LOC_833|>": 101130,
|
823 |
+
"<|LOC_834|>": 101131,
|
824 |
+
"<|LOC_835|>": 101132,
|
825 |
+
"<|LOC_836|>": 101133,
|
826 |
+
"<|LOC_837|>": 101134,
|
827 |
+
"<|LOC_838|>": 101135,
|
828 |
+
"<|LOC_839|>": 101136,
|
829 |
+
"<|LOC_83|>": 100380,
|
830 |
+
"<|LOC_840|>": 101137,
|
831 |
+
"<|LOC_841|>": 101138,
|
832 |
+
"<|LOC_842|>": 101139,
|
833 |
+
"<|LOC_843|>": 101140,
|
834 |
+
"<|LOC_844|>": 101141,
|
835 |
+
"<|LOC_845|>": 101142,
|
836 |
+
"<|LOC_846|>": 101143,
|
837 |
+
"<|LOC_847|>": 101144,
|
838 |
+
"<|LOC_848|>": 101145,
|
839 |
+
"<|LOC_849|>": 101146,
|
840 |
+
"<|LOC_84|>": 100381,
|
841 |
+
"<|LOC_850|>": 101147,
|
842 |
+
"<|LOC_851|>": 101148,
|
843 |
+
"<|LOC_852|>": 101149,
|
844 |
+
"<|LOC_853|>": 101150,
|
845 |
+
"<|LOC_854|>": 101151,
|
846 |
+
"<|LOC_855|>": 101152,
|
847 |
+
"<|LOC_856|>": 101153,
|
848 |
+
"<|LOC_857|>": 101154,
|
849 |
+
"<|LOC_858|>": 101155,
|
850 |
+
"<|LOC_859|>": 101156,
|
851 |
+
"<|LOC_85|>": 100382,
|
852 |
+
"<|LOC_860|>": 101157,
|
853 |
+
"<|LOC_861|>": 101158,
|
854 |
+
"<|LOC_862|>": 101159,
|
855 |
+
"<|LOC_863|>": 101160,
|
856 |
+
"<|LOC_864|>": 101161,
|
857 |
+
"<|LOC_865|>": 101162,
|
858 |
+
"<|LOC_866|>": 101163,
|
859 |
+
"<|LOC_867|>": 101164,
|
860 |
+
"<|LOC_868|>": 101165,
|
861 |
+
"<|LOC_869|>": 101166,
|
862 |
+
"<|LOC_86|>": 100383,
|
863 |
+
"<|LOC_870|>": 101167,
|
864 |
+
"<|LOC_871|>": 101168,
|
865 |
+
"<|LOC_872|>": 101169,
|
866 |
+
"<|LOC_873|>": 101170,
|
867 |
+
"<|LOC_874|>": 101171,
|
868 |
+
"<|LOC_875|>": 101172,
|
869 |
+
"<|LOC_876|>": 101173,
|
870 |
+
"<|LOC_877|>": 101174,
|
871 |
+
"<|LOC_878|>": 101175,
|
872 |
+
"<|LOC_879|>": 101176,
|
873 |
+
"<|LOC_87|>": 100384,
|
874 |
+
"<|LOC_880|>": 101177,
|
875 |
+
"<|LOC_881|>": 101178,
|
876 |
+
"<|LOC_882|>": 101179,
|
877 |
+
"<|LOC_883|>": 101180,
|
878 |
+
"<|LOC_884|>": 101181,
|
879 |
+
"<|LOC_885|>": 101182,
|
880 |
+
"<|LOC_886|>": 101183,
|
881 |
+
"<|LOC_887|>": 101184,
|
882 |
+
"<|LOC_888|>": 101185,
|
883 |
+
"<|LOC_889|>": 101186,
|
884 |
+
"<|LOC_88|>": 100385,
|
885 |
+
"<|LOC_890|>": 101187,
|
886 |
+
"<|LOC_891|>": 101188,
|
887 |
+
"<|LOC_892|>": 101189,
|
888 |
+
"<|LOC_893|>": 101190,
|
889 |
+
"<|LOC_894|>": 101191,
|
890 |
+
"<|LOC_895|>": 101192,
|
891 |
+
"<|LOC_896|>": 101193,
|
892 |
+
"<|LOC_897|>": 101194,
|
893 |
+
"<|LOC_898|>": 101195,
|
894 |
+
"<|LOC_899|>": 101196,
|
895 |
+
"<|LOC_89|>": 100386,
|
896 |
+
"<|LOC_8|>": 100305,
|
897 |
+
"<|LOC_900|>": 101197,
|
898 |
+
"<|LOC_901|>": 101198,
|
899 |
+
"<|LOC_902|>": 101199,
|
900 |
+
"<|LOC_903|>": 101200,
|
901 |
+
"<|LOC_904|>": 101201,
|
902 |
+
"<|LOC_905|>": 101202,
|
903 |
+
"<|LOC_906|>": 101203,
|
904 |
+
"<|LOC_907|>": 101204,
|
905 |
+
"<|LOC_908|>": 101205,
|
906 |
+
"<|LOC_909|>": 101206,
|
907 |
+
"<|LOC_90|>": 100387,
|
908 |
+
"<|LOC_910|>": 101207,
|
909 |
+
"<|LOC_911|>": 101208,
|
910 |
+
"<|LOC_912|>": 101209,
|
911 |
+
"<|LOC_913|>": 101210,
|
912 |
+
"<|LOC_914|>": 101211,
|
913 |
+
"<|LOC_915|>": 101212,
|
914 |
+
"<|LOC_916|>": 101213,
|
915 |
+
"<|LOC_917|>": 101214,
|
916 |
+
"<|LOC_918|>": 101215,
|
917 |
+
"<|LOC_919|>": 101216,
|
918 |
+
"<|LOC_91|>": 100388,
|
919 |
+
"<|LOC_920|>": 101217,
|
920 |
+
"<|LOC_921|>": 101218,
|
921 |
+
"<|LOC_922|>": 101219,
|
922 |
+
"<|LOC_923|>": 101220,
|
923 |
+
"<|LOC_924|>": 101221,
|
924 |
+
"<|LOC_925|>": 101222,
|
925 |
+
"<|LOC_926|>": 101223,
|
926 |
+
"<|LOC_927|>": 101224,
|
927 |
+
"<|LOC_928|>": 101225,
|
928 |
+
"<|LOC_929|>": 101226,
|
929 |
+
"<|LOC_92|>": 100389,
|
930 |
+
"<|LOC_930|>": 101227,
|
931 |
+
"<|LOC_931|>": 101228,
|
932 |
+
"<|LOC_932|>": 101229,
|
933 |
+
"<|LOC_933|>": 101230,
|
934 |
+
"<|LOC_934|>": 101231,
|
935 |
+
"<|LOC_935|>": 101232,
|
936 |
+
"<|LOC_936|>": 101233,
|
937 |
+
"<|LOC_937|>": 101234,
|
938 |
+
"<|LOC_938|>": 101235,
|
939 |
+
"<|LOC_939|>": 101236,
|
940 |
+
"<|LOC_93|>": 100390,
|
941 |
+
"<|LOC_940|>": 101237,
|
942 |
+
"<|LOC_941|>": 101238,
|
943 |
+
"<|LOC_942|>": 101239,
|
944 |
+
"<|LOC_943|>": 101240,
|
945 |
+
"<|LOC_944|>": 101241,
|
946 |
+
"<|LOC_945|>": 101242,
|
947 |
+
"<|LOC_946|>": 101243,
|
948 |
+
"<|LOC_947|>": 101244,
|
949 |
+
"<|LOC_948|>": 101245,
|
950 |
+
"<|LOC_949|>": 101246,
|
951 |
+
"<|LOC_94|>": 100391,
|
952 |
+
"<|LOC_950|>": 101247,
|
953 |
+
"<|LOC_951|>": 101248,
|
954 |
+
"<|LOC_952|>": 101249,
|
955 |
+
"<|LOC_953|>": 101250,
|
956 |
+
"<|LOC_954|>": 101251,
|
957 |
+
"<|LOC_955|>": 101252,
|
958 |
+
"<|LOC_956|>": 101253,
|
959 |
+
"<|LOC_957|>": 101254,
|
960 |
+
"<|LOC_958|>": 101255,
|
961 |
+
"<|LOC_959|>": 101256,
|
962 |
+
"<|LOC_95|>": 100392,
|
963 |
+
"<|LOC_960|>": 101257,
|
964 |
+
"<|LOC_961|>": 101258,
|
965 |
+
"<|LOC_962|>": 101259,
|
966 |
+
"<|LOC_963|>": 101260,
|
967 |
+
"<|LOC_964|>": 101261,
|
968 |
+
"<|LOC_965|>": 101262,
|
969 |
+
"<|LOC_966|>": 101263,
|
970 |
+
"<|LOC_967|>": 101264,
|
971 |
+
"<|LOC_968|>": 101265,
|
972 |
+
"<|LOC_969|>": 101266,
|
973 |
+
"<|LOC_96|>": 100393,
|
974 |
+
"<|LOC_970|>": 101267,
|
975 |
+
"<|LOC_971|>": 101268,
|
976 |
+
"<|LOC_972|>": 101269,
|
977 |
+
"<|LOC_973|>": 101270,
|
978 |
+
"<|LOC_974|>": 101271,
|
979 |
+
"<|LOC_975|>": 101272,
|
980 |
+
"<|LOC_976|>": 101273,
|
981 |
+
"<|LOC_977|>": 101274,
|
982 |
+
"<|LOC_978|>": 101275,
|
983 |
+
"<|LOC_979|>": 101276,
|
984 |
+
"<|LOC_97|>": 100394,
|
985 |
+
"<|LOC_980|>": 101277,
|
986 |
+
"<|LOC_981|>": 101278,
|
987 |
+
"<|LOC_982|>": 101279,
|
988 |
+
"<|LOC_983|>": 101280,
|
989 |
+
"<|LOC_984|>": 101281,
|
990 |
+
"<|LOC_985|>": 101282,
|
991 |
+
"<|LOC_986|>": 101283,
|
992 |
+
"<|LOC_987|>": 101284,
|
993 |
+
"<|LOC_988|>": 101285,
|
994 |
+
"<|LOC_989|>": 101286,
|
995 |
+
"<|LOC_98|>": 100395,
|
996 |
+
"<|LOC_990|>": 101287,
|
997 |
+
"<|LOC_991|>": 101288,
|
998 |
+
"<|LOC_992|>": 101289,
|
999 |
+
"<|LOC_993|>": 101290,
|
1000 |
+
"<|LOC_994|>": 101291,
|
1001 |
+
"<|LOC_995|>": 101292,
|
1002 |
+
"<|LOC_996|>": 101293,
|
1003 |
+
"<|LOC_997|>": 101294,
|
1004 |
+
"<|LOC_998|>": 101295,
|
1005 |
+
"<|LOC_999|>": 101296,
|
1006 |
+
"<|LOC_99|>": 100396,
|
1007 |
+
"<|LOC_9|>": 100306,
|
1008 |
+
"<|LOC_BEGIN|>": 101298,
|
1009 |
+
"<|LOC_END|>": 101299,
|
1010 |
+
"<|LOC_SEP|>": 101300
|
1011 |
+
}
|
test/chat_template.jinja
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{%- if not add_generation_prompt is defined -%}
|
2 |
+
{%- set add_generation_prompt = true -%}
|
3 |
+
{%- endif -%}
|
4 |
+
{%- if not cls_token is defined -%}
|
5 |
+
{%- set cls_token = "<|begin_of_sentence|>" -%}
|
6 |
+
{%- endif -%}
|
7 |
+
{%- if not sep_token is defined -%}
|
8 |
+
{%- set sep_token = "<|end_of_sentence|>" -%}
|
9 |
+
{%- endif -%}
|
10 |
+
{{- cls_token -}}
|
11 |
+
{%- for message in messages -%}
|
12 |
+
{%- if message["role"] == "user" -%}
|
13 |
+
{{- "User: " + message["content"] + "
|
14 |
+
" -}}
|
15 |
+
{%- elif message["role"] == "assistant" -%}
|
16 |
+
{{- "Assistant: " + message["content"] + sep_token -}}
|
17 |
+
{%- elif message["role"] == "system" -%}
|
18 |
+
{{- message["content"] + "
|
19 |
+
" -}}
|
20 |
+
{%- endif -%}
|
21 |
+
{%- endfor -%}
|
22 |
+
{%- if add_generation_prompt -%}
|
23 |
+
{{- "Assistant: " -}}
|
24 |
+
{%- endif -%}
|
test/special_tokens_map.json
ADDED
@@ -0,0 +1,1062 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|IMAGE_PLACEHOLDER|>",
|
4 |
+
"<|AUDIO_PLACEHOLDER|>",
|
5 |
+
"<|LOC_0|>",
|
6 |
+
"<|LOC_1|>",
|
7 |
+
"<|LOC_2|>",
|
8 |
+
"<|LOC_3|>",
|
9 |
+
"<|LOC_4|>",
|
10 |
+
"<|LOC_5|>",
|
11 |
+
"<|LOC_6|>",
|
12 |
+
"<|LOC_7|>",
|
13 |
+
"<|LOC_8|>",
|
14 |
+
"<|LOC_9|>",
|
15 |
+
"<|LOC_10|>",
|
16 |
+
"<|LOC_11|>",
|
17 |
+
"<|LOC_12|>",
|
18 |
+
"<|LOC_13|>",
|
19 |
+
"<|LOC_14|>",
|
20 |
+
"<|LOC_15|>",
|
21 |
+
"<|LOC_16|>",
|
22 |
+
"<|LOC_17|>",
|
23 |
+
"<|LOC_18|>",
|
24 |
+
"<|LOC_19|>",
|
25 |
+
"<|LOC_20|>",
|
26 |
+
"<|LOC_21|>",
|
27 |
+
"<|LOC_22|>",
|
28 |
+
"<|LOC_23|>",
|
29 |
+
"<|LOC_24|>",
|
30 |
+
"<|LOC_25|>",
|
31 |
+
"<|LOC_26|>",
|
32 |
+
"<|LOC_27|>",
|
33 |
+
"<|LOC_28|>",
|
34 |
+
"<|LOC_29|>",
|
35 |
+
"<|LOC_30|>",
|
36 |
+
"<|LOC_31|>",
|
37 |
+
"<|LOC_32|>",
|
38 |
+
"<|LOC_33|>",
|
39 |
+
"<|LOC_34|>",
|
40 |
+
"<|LOC_35|>",
|
41 |
+
"<|LOC_36|>",
|
42 |
+
"<|LOC_37|>",
|
43 |
+
"<|LOC_38|>",
|
44 |
+
"<|LOC_39|>",
|
45 |
+
"<|LOC_40|>",
|
46 |
+
"<|LOC_41|>",
|
47 |
+
"<|LOC_42|>",
|
48 |
+
"<|LOC_43|>",
|
49 |
+
"<|LOC_44|>",
|
50 |
+
"<|LOC_45|>",
|
51 |
+
"<|LOC_46|>",
|
52 |
+
"<|LOC_47|>",
|
53 |
+
"<|LOC_48|>",
|
54 |
+
"<|LOC_49|>",
|
55 |
+
"<|LOC_50|>",
|
56 |
+
"<|LOC_51|>",
|
57 |
+
"<|LOC_52|>",
|
58 |
+
"<|LOC_53|>",
|
59 |
+
"<|LOC_54|>",
|
60 |
+
"<|LOC_55|>",
|
61 |
+
"<|LOC_56|>",
|
62 |
+
"<|LOC_57|>",
|
63 |
+
"<|LOC_58|>",
|
64 |
+
"<|LOC_59|>",
|
65 |
+
"<|LOC_60|>",
|
66 |
+
"<|LOC_61|>",
|
67 |
+
"<|LOC_62|>",
|
68 |
+
"<|LOC_63|>",
|
69 |
+
"<|LOC_64|>",
|
70 |
+
"<|LOC_65|>",
|
71 |
+
"<|LOC_66|>",
|
72 |
+
"<|LOC_67|>",
|
73 |
+
"<|LOC_68|>",
|
74 |
+
"<|LOC_69|>",
|
75 |
+
"<|LOC_70|>",
|
76 |
+
"<|LOC_71|>",
|
77 |
+
"<|LOC_72|>",
|
78 |
+
"<|LOC_73|>",
|
79 |
+
"<|LOC_74|>",
|
80 |
+
"<|LOC_75|>",
|
81 |
+
"<|LOC_76|>",
|
82 |
+
"<|LOC_77|>",
|
83 |
+
"<|LOC_78|>",
|
84 |
+
"<|LOC_79|>",
|
85 |
+
"<|LOC_80|>",
|
86 |
+
"<|LOC_81|>",
|
87 |
+
"<|LOC_82|>",
|
88 |
+
"<|LOC_83|>",
|
89 |
+
"<|LOC_84|>",
|
90 |
+
"<|LOC_85|>",
|
91 |
+
"<|LOC_86|>",
|
92 |
+
"<|LOC_87|>",
|
93 |
+
"<|LOC_88|>",
|
94 |
+
"<|LOC_89|>",
|
95 |
+
"<|LOC_90|>",
|
96 |
+
"<|LOC_91|>",
|
97 |
+
"<|LOC_92|>",
|
98 |
+
"<|LOC_93|>",
|
99 |
+
"<|LOC_94|>",
|
100 |
+
"<|LOC_95|>",
|
101 |
+
"<|LOC_96|>",
|
102 |
+
"<|LOC_97|>",
|
103 |
+
"<|LOC_98|>",
|
104 |
+
"<|LOC_99|>",
|
105 |
+
"<|LOC_100|>",
|
106 |
+
"<|LOC_101|>",
|
107 |
+
"<|LOC_102|>",
|
108 |
+
"<|LOC_103|>",
|
109 |
+
"<|LOC_104|>",
|
110 |
+
"<|LOC_105|>",
|
111 |
+
"<|LOC_106|>",
|
112 |
+
"<|LOC_107|>",
|
113 |
+
"<|LOC_108|>",
|
114 |
+
"<|LOC_109|>",
|
115 |
+
"<|LOC_110|>",
|
116 |
+
"<|LOC_111|>",
|
117 |
+
"<|LOC_112|>",
|
118 |
+
"<|LOC_113|>",
|
119 |
+
"<|LOC_114|>",
|
120 |
+
"<|LOC_115|>",
|
121 |
+
"<|LOC_116|>",
|
122 |
+
"<|LOC_117|>",
|
123 |
+
"<|LOC_118|>",
|
124 |
+
"<|LOC_119|>",
|
125 |
+
"<|LOC_120|>",
|
126 |
+
"<|LOC_121|>",
|
127 |
+
"<|LOC_122|>",
|
128 |
+
"<|LOC_123|>",
|
129 |
+
"<|LOC_124|>",
|
130 |
+
"<|LOC_125|>",
|
131 |
+
"<|LOC_126|>",
|
132 |
+
"<|LOC_127|>",
|
133 |
+
"<|LOC_128|>",
|
134 |
+
"<|LOC_129|>",
|
135 |
+
"<|LOC_130|>",
|
136 |
+
"<|LOC_131|>",
|
137 |
+
"<|LOC_132|>",
|
138 |
+
"<|LOC_133|>",
|
139 |
+
"<|LOC_134|>",
|
140 |
+
"<|LOC_135|>",
|
141 |
+
"<|LOC_136|>",
|
142 |
+
"<|LOC_137|>",
|
143 |
+
"<|LOC_138|>",
|
144 |
+
"<|LOC_139|>",
|
145 |
+
"<|LOC_140|>",
|
146 |
+
"<|LOC_141|>",
|
147 |
+
"<|LOC_142|>",
|
148 |
+
"<|LOC_143|>",
|
149 |
+
"<|LOC_144|>",
|
150 |
+
"<|LOC_145|>",
|
151 |
+
"<|LOC_146|>",
|
152 |
+
"<|LOC_147|>",
|
153 |
+
"<|LOC_148|>",
|
154 |
+
"<|LOC_149|>",
|
155 |
+
"<|LOC_150|>",
|
156 |
+
"<|LOC_151|>",
|
157 |
+
"<|LOC_152|>",
|
158 |
+
"<|LOC_153|>",
|
159 |
+
"<|LOC_154|>",
|
160 |
+
"<|LOC_155|>",
|
161 |
+
"<|LOC_156|>",
|
162 |
+
"<|LOC_157|>",
|
163 |
+
"<|LOC_158|>",
|
164 |
+
"<|LOC_159|>",
|
165 |
+
"<|LOC_160|>",
|
166 |
+
"<|LOC_161|>",
|
167 |
+
"<|LOC_162|>",
|
168 |
+
"<|LOC_163|>",
|
169 |
+
"<|LOC_164|>",
|
170 |
+
"<|LOC_165|>",
|
171 |
+
"<|LOC_166|>",
|
172 |
+
"<|LOC_167|>",
|
173 |
+
"<|LOC_168|>",
|
174 |
+
"<|LOC_169|>",
|
175 |
+
"<|LOC_170|>",
|
176 |
+
"<|LOC_171|>",
|
177 |
+
"<|LOC_172|>",
|
178 |
+
"<|LOC_173|>",
|
179 |
+
"<|LOC_174|>",
|
180 |
+
"<|LOC_175|>",
|
181 |
+
"<|LOC_176|>",
|
182 |
+
"<|LOC_177|>",
|
183 |
+
"<|LOC_178|>",
|
184 |
+
"<|LOC_179|>",
|
185 |
+
"<|LOC_180|>",
|
186 |
+
"<|LOC_181|>",
|
187 |
+
"<|LOC_182|>",
|
188 |
+
"<|LOC_183|>",
|
189 |
+
"<|LOC_184|>",
|
190 |
+
"<|LOC_185|>",
|
191 |
+
"<|LOC_186|>",
|
192 |
+
"<|LOC_187|>",
|
193 |
+
"<|LOC_188|>",
|
194 |
+
"<|LOC_189|>",
|
195 |
+
"<|LOC_190|>",
|
196 |
+
"<|LOC_191|>",
|
197 |
+
"<|LOC_192|>",
|
198 |
+
"<|LOC_193|>",
|
199 |
+
"<|LOC_194|>",
|
200 |
+
"<|LOC_195|>",
|
201 |
+
"<|LOC_196|>",
|
202 |
+
"<|LOC_197|>",
|
203 |
+
"<|LOC_198|>",
|
204 |
+
"<|LOC_199|>",
|
205 |
+
"<|LOC_200|>",
|
206 |
+
"<|LOC_201|>",
|
207 |
+
"<|LOC_202|>",
|
208 |
+
"<|LOC_203|>",
|
209 |
+
"<|LOC_204|>",
|
210 |
+
"<|LOC_205|>",
|
211 |
+
"<|LOC_206|>",
|
212 |
+
"<|LOC_207|>",
|
213 |
+
"<|LOC_208|>",
|
214 |
+
"<|LOC_209|>",
|
215 |
+
"<|LOC_210|>",
|
216 |
+
"<|LOC_211|>",
|
217 |
+
"<|LOC_212|>",
|
218 |
+
"<|LOC_213|>",
|
219 |
+
"<|LOC_214|>",
|
220 |
+
"<|LOC_215|>",
|
221 |
+
"<|LOC_216|>",
|
222 |
+
"<|LOC_217|>",
|
223 |
+
"<|LOC_218|>",
|
224 |
+
"<|LOC_219|>",
|
225 |
+
"<|LOC_220|>",
|
226 |
+
"<|LOC_221|>",
|
227 |
+
"<|LOC_222|>",
|
228 |
+
"<|LOC_223|>",
|
229 |
+
"<|LOC_224|>",
|
230 |
+
"<|LOC_225|>",
|
231 |
+
"<|LOC_226|>",
|
232 |
+
"<|LOC_227|>",
|
233 |
+
"<|LOC_228|>",
|
234 |
+
"<|LOC_229|>",
|
235 |
+
"<|LOC_230|>",
|
236 |
+
"<|LOC_231|>",
|
237 |
+
"<|LOC_232|>",
|
238 |
+
"<|LOC_233|>",
|
239 |
+
"<|LOC_234|>",
|
240 |
+
"<|LOC_235|>",
|
241 |
+
"<|LOC_236|>",
|
242 |
+
"<|LOC_237|>",
|
243 |
+
"<|LOC_238|>",
|
244 |
+
"<|LOC_239|>",
|
245 |
+
"<|LOC_240|>",
|
246 |
+
"<|LOC_241|>",
|
247 |
+
"<|LOC_242|>",
|
248 |
+
"<|LOC_243|>",
|
249 |
+
"<|LOC_244|>",
|
250 |
+
"<|LOC_245|>",
|
251 |
+
"<|LOC_246|>",
|
252 |
+
"<|LOC_247|>",
|
253 |
+
"<|LOC_248|>",
|
254 |
+
"<|LOC_249|>",
|
255 |
+
"<|LOC_250|>",
|
256 |
+
"<|LOC_251|>",
|
257 |
+
"<|LOC_252|>",
|
258 |
+
"<|LOC_253|>",
|
259 |
+
"<|LOC_254|>",
|
260 |
+
"<|LOC_255|>",
|
261 |
+
"<|LOC_256|>",
|
262 |
+
"<|LOC_257|>",
|
263 |
+
"<|LOC_258|>",
|
264 |
+
"<|LOC_259|>",
|
265 |
+
"<|LOC_260|>",
|
266 |
+
"<|LOC_261|>",
|
267 |
+
"<|LOC_262|>",
|
268 |
+
"<|LOC_263|>",
|
269 |
+
"<|LOC_264|>",
|
270 |
+
"<|LOC_265|>",
|
271 |
+
"<|LOC_266|>",
|
272 |
+
"<|LOC_267|>",
|
273 |
+
"<|LOC_268|>",
|
274 |
+
"<|LOC_269|>",
|
275 |
+
"<|LOC_270|>",
|
276 |
+
"<|LOC_271|>",
|
277 |
+
"<|LOC_272|>",
|
278 |
+
"<|LOC_273|>",
|
279 |
+
"<|LOC_274|>",
|
280 |
+
"<|LOC_275|>",
|
281 |
+
"<|LOC_276|>",
|
282 |
+
"<|LOC_277|>",
|
283 |
+
"<|LOC_278|>",
|
284 |
+
"<|LOC_279|>",
|
285 |
+
"<|LOC_280|>",
|
286 |
+
"<|LOC_281|>",
|
287 |
+
"<|LOC_282|>",
|
288 |
+
"<|LOC_283|>",
|
289 |
+
"<|LOC_284|>",
|
290 |
+
"<|LOC_285|>",
|
291 |
+
"<|LOC_286|>",
|
292 |
+
"<|LOC_287|>",
|
293 |
+
"<|LOC_288|>",
|
294 |
+
"<|LOC_289|>",
|
295 |
+
"<|LOC_290|>",
|
296 |
+
"<|LOC_291|>",
|
297 |
+
"<|LOC_292|>",
|
298 |
+
"<|LOC_293|>",
|
299 |
+
"<|LOC_294|>",
|
300 |
+
"<|LOC_295|>",
|
301 |
+
"<|LOC_296|>",
|
302 |
+
"<|LOC_297|>",
|
303 |
+
"<|LOC_298|>",
|
304 |
+
"<|LOC_299|>",
|
305 |
+
"<|LOC_300|>",
|
306 |
+
"<|LOC_301|>",
|
307 |
+
"<|LOC_302|>",
|
308 |
+
"<|LOC_303|>",
|
309 |
+
"<|LOC_304|>",
|
310 |
+
"<|LOC_305|>",
|
311 |
+
"<|LOC_306|>",
|
312 |
+
"<|LOC_307|>",
|
313 |
+
"<|LOC_308|>",
|
314 |
+
"<|LOC_309|>",
|
315 |
+
"<|LOC_310|>",
|
316 |
+
"<|LOC_311|>",
|
317 |
+
"<|LOC_312|>",
|
318 |
+
"<|LOC_313|>",
|
319 |
+
"<|LOC_314|>",
|
320 |
+
"<|LOC_315|>",
|
321 |
+
"<|LOC_316|>",
|
322 |
+
"<|LOC_317|>",
|
323 |
+
"<|LOC_318|>",
|
324 |
+
"<|LOC_319|>",
|
325 |
+
"<|LOC_320|>",
|
326 |
+
"<|LOC_321|>",
|
327 |
+
"<|LOC_322|>",
|
328 |
+
"<|LOC_323|>",
|
329 |
+
"<|LOC_324|>",
|
330 |
+
"<|LOC_325|>",
|
331 |
+
"<|LOC_326|>",
|
332 |
+
"<|LOC_327|>",
|
333 |
+
"<|LOC_328|>",
|
334 |
+
"<|LOC_329|>",
|
335 |
+
"<|LOC_330|>",
|
336 |
+
"<|LOC_331|>",
|
337 |
+
"<|LOC_332|>",
|
338 |
+
"<|LOC_333|>",
|
339 |
+
"<|LOC_334|>",
|
340 |
+
"<|LOC_335|>",
|
341 |
+
"<|LOC_336|>",
|
342 |
+
"<|LOC_337|>",
|
343 |
+
"<|LOC_338|>",
|
344 |
+
"<|LOC_339|>",
|
345 |
+
"<|LOC_340|>",
|
346 |
+
"<|LOC_341|>",
|
347 |
+
"<|LOC_342|>",
|
348 |
+
"<|LOC_343|>",
|
349 |
+
"<|LOC_344|>",
|
350 |
+
"<|LOC_345|>",
|
351 |
+
"<|LOC_346|>",
|
352 |
+
"<|LOC_347|>",
|
353 |
+
"<|LOC_348|>",
|
354 |
+
"<|LOC_349|>",
|
355 |
+
"<|LOC_350|>",
|
356 |
+
"<|LOC_351|>",
|
357 |
+
"<|LOC_352|>",
|
358 |
+
"<|LOC_353|>",
|
359 |
+
"<|LOC_354|>",
|
360 |
+
"<|LOC_355|>",
|
361 |
+
"<|LOC_356|>",
|
362 |
+
"<|LOC_357|>",
|
363 |
+
"<|LOC_358|>",
|
364 |
+
"<|LOC_359|>",
|
365 |
+
"<|LOC_360|>",
|
366 |
+
"<|LOC_361|>",
|
367 |
+
"<|LOC_362|>",
|
368 |
+
"<|LOC_363|>",
|
369 |
+
"<|LOC_364|>",
|
370 |
+
"<|LOC_365|>",
|
371 |
+
"<|LOC_366|>",
|
372 |
+
"<|LOC_367|>",
|
373 |
+
"<|LOC_368|>",
|
374 |
+
"<|LOC_369|>",
|
375 |
+
"<|LOC_370|>",
|
376 |
+
"<|LOC_371|>",
|
377 |
+
"<|LOC_372|>",
|
378 |
+
"<|LOC_373|>",
|
379 |
+
"<|LOC_374|>",
|
380 |
+
"<|LOC_375|>",
|
381 |
+
"<|LOC_376|>",
|
382 |
+
"<|LOC_377|>",
|
383 |
+
"<|LOC_378|>",
|
384 |
+
"<|LOC_379|>",
|
385 |
+
"<|LOC_380|>",
|
386 |
+
"<|LOC_381|>",
|
387 |
+
"<|LOC_382|>",
|
388 |
+
"<|LOC_383|>",
|
389 |
+
"<|LOC_384|>",
|
390 |
+
"<|LOC_385|>",
|
391 |
+
"<|LOC_386|>",
|
392 |
+
"<|LOC_387|>",
|
393 |
+
"<|LOC_388|>",
|
394 |
+
"<|LOC_389|>",
|
395 |
+
"<|LOC_390|>",
|
396 |
+
"<|LOC_391|>",
|
397 |
+
"<|LOC_392|>",
|
398 |
+
"<|LOC_393|>",
|
399 |
+
"<|LOC_394|>",
|
400 |
+
"<|LOC_395|>",
|
401 |
+
"<|LOC_396|>",
|
402 |
+
"<|LOC_397|>",
|
403 |
+
"<|LOC_398|>",
|
404 |
+
"<|LOC_399|>",
|
405 |
+
"<|LOC_400|>",
|
406 |
+
"<|LOC_401|>",
|
407 |
+
"<|LOC_402|>",
|
408 |
+
"<|LOC_403|>",
|
409 |
+
"<|LOC_404|>",
|
410 |
+
"<|LOC_405|>",
|
411 |
+
"<|LOC_406|>",
|
412 |
+
"<|LOC_407|>",
|
413 |
+
"<|LOC_408|>",
|
414 |
+
"<|LOC_409|>",
|
415 |
+
"<|LOC_410|>",
|
416 |
+
"<|LOC_411|>",
|
417 |
+
"<|LOC_412|>",
|
418 |
+
"<|LOC_413|>",
|
419 |
+
"<|LOC_414|>",
|
420 |
+
"<|LOC_415|>",
|
421 |
+
"<|LOC_416|>",
|
422 |
+
"<|LOC_417|>",
|
423 |
+
"<|LOC_418|>",
|
424 |
+
"<|LOC_419|>",
|
425 |
+
"<|LOC_420|>",
|
426 |
+
"<|LOC_421|>",
|
427 |
+
"<|LOC_422|>",
|
428 |
+
"<|LOC_423|>",
|
429 |
+
"<|LOC_424|>",
|
430 |
+
"<|LOC_425|>",
|
431 |
+
"<|LOC_426|>",
|
432 |
+
"<|LOC_427|>",
|
433 |
+
"<|LOC_428|>",
|
434 |
+
"<|LOC_429|>",
|
435 |
+
"<|LOC_430|>",
|
436 |
+
"<|LOC_431|>",
|
437 |
+
"<|LOC_432|>",
|
438 |
+
"<|LOC_433|>",
|
439 |
+
"<|LOC_434|>",
|
440 |
+
"<|LOC_435|>",
|
441 |
+
"<|LOC_436|>",
|
442 |
+
"<|LOC_437|>",
|
443 |
+
"<|LOC_438|>",
|
444 |
+
"<|LOC_439|>",
|
445 |
+
"<|LOC_440|>",
|
446 |
+
"<|LOC_441|>",
|
447 |
+
"<|LOC_442|>",
|
448 |
+
"<|LOC_443|>",
|
449 |
+
"<|LOC_444|>",
|
450 |
+
"<|LOC_445|>",
|
451 |
+
"<|LOC_446|>",
|
452 |
+
"<|LOC_447|>",
|
453 |
+
"<|LOC_448|>",
|
454 |
+
"<|LOC_449|>",
|
455 |
+
"<|LOC_450|>",
|
456 |
+
"<|LOC_451|>",
|
457 |
+
"<|LOC_452|>",
|
458 |
+
"<|LOC_453|>",
|
459 |
+
"<|LOC_454|>",
|
460 |
+
"<|LOC_455|>",
|
461 |
+
"<|LOC_456|>",
|
462 |
+
"<|LOC_457|>",
|
463 |
+
"<|LOC_458|>",
|
464 |
+
"<|LOC_459|>",
|
465 |
+
"<|LOC_460|>",
|
466 |
+
"<|LOC_461|>",
|
467 |
+
"<|LOC_462|>",
|
468 |
+
"<|LOC_463|>",
|
469 |
+
"<|LOC_464|>",
|
470 |
+
"<|LOC_465|>",
|
471 |
+
"<|LOC_466|>",
|
472 |
+
"<|LOC_467|>",
|
473 |
+
"<|LOC_468|>",
|
474 |
+
"<|LOC_469|>",
|
475 |
+
"<|LOC_470|>",
|
476 |
+
"<|LOC_471|>",
|
477 |
+
"<|LOC_472|>",
|
478 |
+
"<|LOC_473|>",
|
479 |
+
"<|LOC_474|>",
|
480 |
+
"<|LOC_475|>",
|
481 |
+
"<|LOC_476|>",
|
482 |
+
"<|LOC_477|>",
|
483 |
+
"<|LOC_478|>",
|
484 |
+
"<|LOC_479|>",
|
485 |
+
"<|LOC_480|>",
|
486 |
+
"<|LOC_481|>",
|
487 |
+
"<|LOC_482|>",
|
488 |
+
"<|LOC_483|>",
|
489 |
+
"<|LOC_484|>",
|
490 |
+
"<|LOC_485|>",
|
491 |
+
"<|LOC_486|>",
|
492 |
+
"<|LOC_487|>",
|
493 |
+
"<|LOC_488|>",
|
494 |
+
"<|LOC_489|>",
|
495 |
+
"<|LOC_490|>",
|
496 |
+
"<|LOC_491|>",
|
497 |
+
"<|LOC_492|>",
|
498 |
+
"<|LOC_493|>",
|
499 |
+
"<|LOC_494|>",
|
500 |
+
"<|LOC_495|>",
|
501 |
+
"<|LOC_496|>",
|
502 |
+
"<|LOC_497|>",
|
503 |
+
"<|LOC_498|>",
|
504 |
+
"<|LOC_499|>",
|
505 |
+
"<|LOC_500|>",
|
506 |
+
"<|LOC_501|>",
|
507 |
+
"<|LOC_502|>",
|
508 |
+
"<|LOC_503|>",
|
509 |
+
"<|LOC_504|>",
|
510 |
+
"<|LOC_505|>",
|
511 |
+
"<|LOC_506|>",
|
512 |
+
"<|LOC_507|>",
|
513 |
+
"<|LOC_508|>",
|
514 |
+
"<|LOC_509|>",
|
515 |
+
"<|LOC_510|>",
|
516 |
+
"<|LOC_511|>",
|
517 |
+
"<|LOC_512|>",
|
518 |
+
"<|LOC_513|>",
|
519 |
+
"<|LOC_514|>",
|
520 |
+
"<|LOC_515|>",
|
521 |
+
"<|LOC_516|>",
|
522 |
+
"<|LOC_517|>",
|
523 |
+
"<|LOC_518|>",
|
524 |
+
"<|LOC_519|>",
|
525 |
+
"<|LOC_520|>",
|
526 |
+
"<|LOC_521|>",
|
527 |
+
"<|LOC_522|>",
|
528 |
+
"<|LOC_523|>",
|
529 |
+
"<|LOC_524|>",
|
530 |
+
"<|LOC_525|>",
|
531 |
+
"<|LOC_526|>",
|
532 |
+
"<|LOC_527|>",
|
533 |
+
"<|LOC_528|>",
|
534 |
+
"<|LOC_529|>",
|
535 |
+
"<|LOC_530|>",
|
536 |
+
"<|LOC_531|>",
|
537 |
+
"<|LOC_532|>",
|
538 |
+
"<|LOC_533|>",
|
539 |
+
"<|LOC_534|>",
|
540 |
+
"<|LOC_535|>",
|
541 |
+
"<|LOC_536|>",
|
542 |
+
"<|LOC_537|>",
|
543 |
+
"<|LOC_538|>",
|
544 |
+
"<|LOC_539|>",
|
545 |
+
"<|LOC_540|>",
|
546 |
+
"<|LOC_541|>",
|
547 |
+
"<|LOC_542|>",
|
548 |
+
"<|LOC_543|>",
|
549 |
+
"<|LOC_544|>",
|
550 |
+
"<|LOC_545|>",
|
551 |
+
"<|LOC_546|>",
|
552 |
+
"<|LOC_547|>",
|
553 |
+
"<|LOC_548|>",
|
554 |
+
"<|LOC_549|>",
|
555 |
+
"<|LOC_550|>",
|
556 |
+
"<|LOC_551|>",
|
557 |
+
"<|LOC_552|>",
|
558 |
+
"<|LOC_553|>",
|
559 |
+
"<|LOC_554|>",
|
560 |
+
"<|LOC_555|>",
|
561 |
+
"<|LOC_556|>",
|
562 |
+
"<|LOC_557|>",
|
563 |
+
"<|LOC_558|>",
|
564 |
+
"<|LOC_559|>",
|
565 |
+
"<|LOC_560|>",
|
566 |
+
"<|LOC_561|>",
|
567 |
+
"<|LOC_562|>",
|
568 |
+
"<|LOC_563|>",
|
569 |
+
"<|LOC_564|>",
|
570 |
+
"<|LOC_565|>",
|
571 |
+
"<|LOC_566|>",
|
572 |
+
"<|LOC_567|>",
|
573 |
+
"<|LOC_568|>",
|
574 |
+
"<|LOC_569|>",
|
575 |
+
"<|LOC_570|>",
|
576 |
+
"<|LOC_571|>",
|
577 |
+
"<|LOC_572|>",
|
578 |
+
"<|LOC_573|>",
|
579 |
+
"<|LOC_574|>",
|
580 |
+
"<|LOC_575|>",
|
581 |
+
"<|LOC_576|>",
|
582 |
+
"<|LOC_577|>",
|
583 |
+
"<|LOC_578|>",
|
584 |
+
"<|LOC_579|>",
|
585 |
+
"<|LOC_580|>",
|
586 |
+
"<|LOC_581|>",
|
587 |
+
"<|LOC_582|>",
|
588 |
+
"<|LOC_583|>",
|
589 |
+
"<|LOC_584|>",
|
590 |
+
"<|LOC_585|>",
|
591 |
+
"<|LOC_586|>",
|
592 |
+
"<|LOC_587|>",
|
593 |
+
"<|LOC_588|>",
|
594 |
+
"<|LOC_589|>",
|
595 |
+
"<|LOC_590|>",
|
596 |
+
"<|LOC_591|>",
|
597 |
+
"<|LOC_592|>",
|
598 |
+
"<|LOC_593|>",
|
599 |
+
"<|LOC_594|>",
|
600 |
+
"<|LOC_595|>",
|
601 |
+
"<|LOC_596|>",
|
602 |
+
"<|LOC_597|>",
|
603 |
+
"<|LOC_598|>",
|
604 |
+
"<|LOC_599|>",
|
605 |
+
"<|LOC_600|>",
|
606 |
+
"<|LOC_601|>",
|
607 |
+
"<|LOC_602|>",
|
608 |
+
"<|LOC_603|>",
|
609 |
+
"<|LOC_604|>",
|
610 |
+
"<|LOC_605|>",
|
611 |
+
"<|LOC_606|>",
|
612 |
+
"<|LOC_607|>",
|
613 |
+
"<|LOC_608|>",
|
614 |
+
"<|LOC_609|>",
|
615 |
+
"<|LOC_610|>",
|
616 |
+
"<|LOC_611|>",
|
617 |
+
"<|LOC_612|>",
|
618 |
+
"<|LOC_613|>",
|
619 |
+
"<|LOC_614|>",
|
620 |
+
"<|LOC_615|>",
|
621 |
+
"<|LOC_616|>",
|
622 |
+
"<|LOC_617|>",
|
623 |
+
"<|LOC_618|>",
|
624 |
+
"<|LOC_619|>",
|
625 |
+
"<|LOC_620|>",
|
626 |
+
"<|LOC_621|>",
|
627 |
+
"<|LOC_622|>",
|
628 |
+
"<|LOC_623|>",
|
629 |
+
"<|LOC_624|>",
|
630 |
+
"<|LOC_625|>",
|
631 |
+
"<|LOC_626|>",
|
632 |
+
"<|LOC_627|>",
|
633 |
+
"<|LOC_628|>",
|
634 |
+
"<|LOC_629|>",
|
635 |
+
"<|LOC_630|>",
|
636 |
+
"<|LOC_631|>",
|
637 |
+
"<|LOC_632|>",
|
638 |
+
"<|LOC_633|>",
|
639 |
+
"<|LOC_634|>",
|
640 |
+
"<|LOC_635|>",
|
641 |
+
"<|LOC_636|>",
|
642 |
+
"<|LOC_637|>",
|
643 |
+
"<|LOC_638|>",
|
644 |
+
"<|LOC_639|>",
|
645 |
+
"<|LOC_640|>",
|
646 |
+
"<|LOC_641|>",
|
647 |
+
"<|LOC_642|>",
|
648 |
+
"<|LOC_643|>",
|
649 |
+
"<|LOC_644|>",
|
650 |
+
"<|LOC_645|>",
|
651 |
+
"<|LOC_646|>",
|
652 |
+
"<|LOC_647|>",
|
653 |
+
"<|LOC_648|>",
|
654 |
+
"<|LOC_649|>",
|
655 |
+
"<|LOC_650|>",
|
656 |
+
"<|LOC_651|>",
|
657 |
+
"<|LOC_652|>",
|
658 |
+
"<|LOC_653|>",
|
659 |
+
"<|LOC_654|>",
|
660 |
+
"<|LOC_655|>",
|
661 |
+
"<|LOC_656|>",
|
662 |
+
"<|LOC_657|>",
|
663 |
+
"<|LOC_658|>",
|
664 |
+
"<|LOC_659|>",
|
665 |
+
"<|LOC_660|>",
|
666 |
+
"<|LOC_661|>",
|
667 |
+
"<|LOC_662|>",
|
668 |
+
"<|LOC_663|>",
|
669 |
+
"<|LOC_664|>",
|
670 |
+
"<|LOC_665|>",
|
671 |
+
"<|LOC_666|>",
|
672 |
+
"<|LOC_667|>",
|
673 |
+
"<|LOC_668|>",
|
674 |
+
"<|LOC_669|>",
|
675 |
+
"<|LOC_670|>",
|
676 |
+
"<|LOC_671|>",
|
677 |
+
"<|LOC_672|>",
|
678 |
+
"<|LOC_673|>",
|
679 |
+
"<|LOC_674|>",
|
680 |
+
"<|LOC_675|>",
|
681 |
+
"<|LOC_676|>",
|
682 |
+
"<|LOC_677|>",
|
683 |
+
"<|LOC_678|>",
|
684 |
+
"<|LOC_679|>",
|
685 |
+
"<|LOC_680|>",
|
686 |
+
"<|LOC_681|>",
|
687 |
+
"<|LOC_682|>",
|
688 |
+
"<|LOC_683|>",
|
689 |
+
"<|LOC_684|>",
|
690 |
+
"<|LOC_685|>",
|
691 |
+
"<|LOC_686|>",
|
692 |
+
"<|LOC_687|>",
|
693 |
+
"<|LOC_688|>",
|
694 |
+
"<|LOC_689|>",
|
695 |
+
"<|LOC_690|>",
|
696 |
+
"<|LOC_691|>",
|
697 |
+
"<|LOC_692|>",
|
698 |
+
"<|LOC_693|>",
|
699 |
+
"<|LOC_694|>",
|
700 |
+
"<|LOC_695|>",
|
701 |
+
"<|LOC_696|>",
|
702 |
+
"<|LOC_697|>",
|
703 |
+
"<|LOC_698|>",
|
704 |
+
"<|LOC_699|>",
|
705 |
+
"<|LOC_700|>",
|
706 |
+
"<|LOC_701|>",
|
707 |
+
"<|LOC_702|>",
|
708 |
+
"<|LOC_703|>",
|
709 |
+
"<|LOC_704|>",
|
710 |
+
"<|LOC_705|>",
|
711 |
+
"<|LOC_706|>",
|
712 |
+
"<|LOC_707|>",
|
713 |
+
"<|LOC_708|>",
|
714 |
+
"<|LOC_709|>",
|
715 |
+
"<|LOC_710|>",
|
716 |
+
"<|LOC_711|>",
|
717 |
+
"<|LOC_712|>",
|
718 |
+
"<|LOC_713|>",
|
719 |
+
"<|LOC_714|>",
|
720 |
+
"<|LOC_715|>",
|
721 |
+
"<|LOC_716|>",
|
722 |
+
"<|LOC_717|>",
|
723 |
+
"<|LOC_718|>",
|
724 |
+
"<|LOC_719|>",
|
725 |
+
"<|LOC_720|>",
|
726 |
+
"<|LOC_721|>",
|
727 |
+
"<|LOC_722|>",
|
728 |
+
"<|LOC_723|>",
|
729 |
+
"<|LOC_724|>",
|
730 |
+
"<|LOC_725|>",
|
731 |
+
"<|LOC_726|>",
|
732 |
+
"<|LOC_727|>",
|
733 |
+
"<|LOC_728|>",
|
734 |
+
"<|LOC_729|>",
|
735 |
+
"<|LOC_730|>",
|
736 |
+
"<|LOC_731|>",
|
737 |
+
"<|LOC_732|>",
|
738 |
+
"<|LOC_733|>",
|
739 |
+
"<|LOC_734|>",
|
740 |
+
"<|LOC_735|>",
|
741 |
+
"<|LOC_736|>",
|
742 |
+
"<|LOC_737|>",
|
743 |
+
"<|LOC_738|>",
|
744 |
+
"<|LOC_739|>",
|
745 |
+
"<|LOC_740|>",
|
746 |
+
"<|LOC_741|>",
|
747 |
+
"<|LOC_742|>",
|
748 |
+
"<|LOC_743|>",
|
749 |
+
"<|LOC_744|>",
|
750 |
+
"<|LOC_745|>",
|
751 |
+
"<|LOC_746|>",
|
752 |
+
"<|LOC_747|>",
|
753 |
+
"<|LOC_748|>",
|
754 |
+
"<|LOC_749|>",
|
755 |
+
"<|LOC_750|>",
|
756 |
+
"<|LOC_751|>",
|
757 |
+
"<|LOC_752|>",
|
758 |
+
"<|LOC_753|>",
|
759 |
+
"<|LOC_754|>",
|
760 |
+
"<|LOC_755|>",
|
761 |
+
"<|LOC_756|>",
|
762 |
+
"<|LOC_757|>",
|
763 |
+
"<|LOC_758|>",
|
764 |
+
"<|LOC_759|>",
|
765 |
+
"<|LOC_760|>",
|
766 |
+
"<|LOC_761|>",
|
767 |
+
"<|LOC_762|>",
|
768 |
+
"<|LOC_763|>",
|
769 |
+
"<|LOC_764|>",
|
770 |
+
"<|LOC_765|>",
|
771 |
+
"<|LOC_766|>",
|
772 |
+
"<|LOC_767|>",
|
773 |
+
"<|LOC_768|>",
|
774 |
+
"<|LOC_769|>",
|
775 |
+
"<|LOC_770|>",
|
776 |
+
"<|LOC_771|>",
|
777 |
+
"<|LOC_772|>",
|
778 |
+
"<|LOC_773|>",
|
779 |
+
"<|LOC_774|>",
|
780 |
+
"<|LOC_775|>",
|
781 |
+
"<|LOC_776|>",
|
782 |
+
"<|LOC_777|>",
|
783 |
+
"<|LOC_778|>",
|
784 |
+
"<|LOC_779|>",
|
785 |
+
"<|LOC_780|>",
|
786 |
+
"<|LOC_781|>",
|
787 |
+
"<|LOC_782|>",
|
788 |
+
"<|LOC_783|>",
|
789 |
+
"<|LOC_784|>",
|
790 |
+
"<|LOC_785|>",
|
791 |
+
"<|LOC_786|>",
|
792 |
+
"<|LOC_787|>",
|
793 |
+
"<|LOC_788|>",
|
794 |
+
"<|LOC_789|>",
|
795 |
+
"<|LOC_790|>",
|
796 |
+
"<|LOC_791|>",
|
797 |
+
"<|LOC_792|>",
|
798 |
+
"<|LOC_793|>",
|
799 |
+
"<|LOC_794|>",
|
800 |
+
"<|LOC_795|>",
|
801 |
+
"<|LOC_796|>",
|
802 |
+
"<|LOC_797|>",
|
803 |
+
"<|LOC_798|>",
|
804 |
+
"<|LOC_799|>",
|
805 |
+
"<|LOC_800|>",
|
806 |
+
"<|LOC_801|>",
|
807 |
+
"<|LOC_802|>",
|
808 |
+
"<|LOC_803|>",
|
809 |
+
"<|LOC_804|>",
|
810 |
+
"<|LOC_805|>",
|
811 |
+
"<|LOC_806|>",
|
812 |
+
"<|LOC_807|>",
|
813 |
+
"<|LOC_808|>",
|
814 |
+
"<|LOC_809|>",
|
815 |
+
"<|LOC_810|>",
|
816 |
+
"<|LOC_811|>",
|
817 |
+
"<|LOC_812|>",
|
818 |
+
"<|LOC_813|>",
|
819 |
+
"<|LOC_814|>",
|
820 |
+
"<|LOC_815|>",
|
821 |
+
"<|LOC_816|>",
|
822 |
+
"<|LOC_817|>",
|
823 |
+
"<|LOC_818|>",
|
824 |
+
"<|LOC_819|>",
|
825 |
+
"<|LOC_820|>",
|
826 |
+
"<|LOC_821|>",
|
827 |
+
"<|LOC_822|>",
|
828 |
+
"<|LOC_823|>",
|
829 |
+
"<|LOC_824|>",
|
830 |
+
"<|LOC_825|>",
|
831 |
+
"<|LOC_826|>",
|
832 |
+
"<|LOC_827|>",
|
833 |
+
"<|LOC_828|>",
|
834 |
+
"<|LOC_829|>",
|
835 |
+
"<|LOC_830|>",
|
836 |
+
"<|LOC_831|>",
|
837 |
+
"<|LOC_832|>",
|
838 |
+
"<|LOC_833|>",
|
839 |
+
"<|LOC_834|>",
|
840 |
+
"<|LOC_835|>",
|
841 |
+
"<|LOC_836|>",
|
842 |
+
"<|LOC_837|>",
|
843 |
+
"<|LOC_838|>",
|
844 |
+
"<|LOC_839|>",
|
845 |
+
"<|LOC_840|>",
|
846 |
+
"<|LOC_841|>",
|
847 |
+
"<|LOC_842|>",
|
848 |
+
"<|LOC_843|>",
|
849 |
+
"<|LOC_844|>",
|
850 |
+
"<|LOC_845|>",
|
851 |
+
"<|LOC_846|>",
|
852 |
+
"<|LOC_847|>",
|
853 |
+
"<|LOC_848|>",
|
854 |
+
"<|LOC_849|>",
|
855 |
+
"<|LOC_850|>",
|
856 |
+
"<|LOC_851|>",
|
857 |
+
"<|LOC_852|>",
|
858 |
+
"<|LOC_853|>",
|
859 |
+
"<|LOC_854|>",
|
860 |
+
"<|LOC_855|>",
|
861 |
+
"<|LOC_856|>",
|
862 |
+
"<|LOC_857|>",
|
863 |
+
"<|LOC_858|>",
|
864 |
+
"<|LOC_859|>",
|
865 |
+
"<|LOC_860|>",
|
866 |
+
"<|LOC_861|>",
|
867 |
+
"<|LOC_862|>",
|
868 |
+
"<|LOC_863|>",
|
869 |
+
"<|LOC_864|>",
|
870 |
+
"<|LOC_865|>",
|
871 |
+
"<|LOC_866|>",
|
872 |
+
"<|LOC_867|>",
|
873 |
+
"<|LOC_868|>",
|
874 |
+
"<|LOC_869|>",
|
875 |
+
"<|LOC_870|>",
|
876 |
+
"<|LOC_871|>",
|
877 |
+
"<|LOC_872|>",
|
878 |
+
"<|LOC_873|>",
|
879 |
+
"<|LOC_874|>",
|
880 |
+
"<|LOC_875|>",
|
881 |
+
"<|LOC_876|>",
|
882 |
+
"<|LOC_877|>",
|
883 |
+
"<|LOC_878|>",
|
884 |
+
"<|LOC_879|>",
|
885 |
+
"<|LOC_880|>",
|
886 |
+
"<|LOC_881|>",
|
887 |
+
"<|LOC_882|>",
|
888 |
+
"<|LOC_883|>",
|
889 |
+
"<|LOC_884|>",
|
890 |
+
"<|LOC_885|>",
|
891 |
+
"<|LOC_886|>",
|
892 |
+
"<|LOC_887|>",
|
893 |
+
"<|LOC_888|>",
|
894 |
+
"<|LOC_889|>",
|
895 |
+
"<|LOC_890|>",
|
896 |
+
"<|LOC_891|>",
|
897 |
+
"<|LOC_892|>",
|
898 |
+
"<|LOC_893|>",
|
899 |
+
"<|LOC_894|>",
|
900 |
+
"<|LOC_895|>",
|
901 |
+
"<|LOC_896|>",
|
902 |
+
"<|LOC_897|>",
|
903 |
+
"<|LOC_898|>",
|
904 |
+
"<|LOC_899|>",
|
905 |
+
"<|LOC_900|>",
|
906 |
+
"<|LOC_901|>",
|
907 |
+
"<|LOC_902|>",
|
908 |
+
"<|LOC_903|>",
|
909 |
+
"<|LOC_904|>",
|
910 |
+
"<|LOC_905|>",
|
911 |
+
"<|LOC_906|>",
|
912 |
+
"<|LOC_907|>",
|
913 |
+
"<|LOC_908|>",
|
914 |
+
"<|LOC_909|>",
|
915 |
+
"<|LOC_910|>",
|
916 |
+
"<|LOC_911|>",
|
917 |
+
"<|LOC_912|>",
|
918 |
+
"<|LOC_913|>",
|
919 |
+
"<|LOC_914|>",
|
920 |
+
"<|LOC_915|>",
|
921 |
+
"<|LOC_916|>",
|
922 |
+
"<|LOC_917|>",
|
923 |
+
"<|LOC_918|>",
|
924 |
+
"<|LOC_919|>",
|
925 |
+
"<|LOC_920|>",
|
926 |
+
"<|LOC_921|>",
|
927 |
+
"<|LOC_922|>",
|
928 |
+
"<|LOC_923|>",
|
929 |
+
"<|LOC_924|>",
|
930 |
+
"<|LOC_925|>",
|
931 |
+
"<|LOC_926|>",
|
932 |
+
"<|LOC_927|>",
|
933 |
+
"<|LOC_928|>",
|
934 |
+
"<|LOC_929|>",
|
935 |
+
"<|LOC_930|>",
|
936 |
+
"<|LOC_931|>",
|
937 |
+
"<|LOC_932|>",
|
938 |
+
"<|LOC_933|>",
|
939 |
+
"<|LOC_934|>",
|
940 |
+
"<|LOC_935|>",
|
941 |
+
"<|LOC_936|>",
|
942 |
+
"<|LOC_937|>",
|
943 |
+
"<|LOC_938|>",
|
944 |
+
"<|LOC_939|>",
|
945 |
+
"<|LOC_940|>",
|
946 |
+
"<|LOC_941|>",
|
947 |
+
"<|LOC_942|>",
|
948 |
+
"<|LOC_943|>",
|
949 |
+
"<|LOC_944|>",
|
950 |
+
"<|LOC_945|>",
|
951 |
+
"<|LOC_946|>",
|
952 |
+
"<|LOC_947|>",
|
953 |
+
"<|LOC_948|>",
|
954 |
+
"<|LOC_949|>",
|
955 |
+
"<|LOC_950|>",
|
956 |
+
"<|LOC_951|>",
|
957 |
+
"<|LOC_952|>",
|
958 |
+
"<|LOC_953|>",
|
959 |
+
"<|LOC_954|>",
|
960 |
+
"<|LOC_955|>",
|
961 |
+
"<|LOC_956|>",
|
962 |
+
"<|LOC_957|>",
|
963 |
+
"<|LOC_958|>",
|
964 |
+
"<|LOC_959|>",
|
965 |
+
"<|LOC_960|>",
|
966 |
+
"<|LOC_961|>",
|
967 |
+
"<|LOC_962|>",
|
968 |
+
"<|LOC_963|>",
|
969 |
+
"<|LOC_964|>",
|
970 |
+
"<|LOC_965|>",
|
971 |
+
"<|LOC_966|>",
|
972 |
+
"<|LOC_967|>",
|
973 |
+
"<|LOC_968|>",
|
974 |
+
"<|LOC_969|>",
|
975 |
+
"<|LOC_970|>",
|
976 |
+
"<|LOC_971|>",
|
977 |
+
"<|LOC_972|>",
|
978 |
+
"<|LOC_973|>",
|
979 |
+
"<|LOC_974|>",
|
980 |
+
"<|LOC_975|>",
|
981 |
+
"<|LOC_976|>",
|
982 |
+
"<|LOC_977|>",
|
983 |
+
"<|LOC_978|>",
|
984 |
+
"<|LOC_979|>",
|
985 |
+
"<|LOC_980|>",
|
986 |
+
"<|LOC_981|>",
|
987 |
+
"<|LOC_982|>",
|
988 |
+
"<|LOC_983|>",
|
989 |
+
"<|LOC_984|>",
|
990 |
+
"<|LOC_985|>",
|
991 |
+
"<|LOC_986|>",
|
992 |
+
"<|LOC_987|>",
|
993 |
+
"<|LOC_988|>",
|
994 |
+
"<|LOC_989|>",
|
995 |
+
"<|LOC_990|>",
|
996 |
+
"<|LOC_991|>",
|
997 |
+
"<|LOC_992|>",
|
998 |
+
"<|LOC_993|>",
|
999 |
+
"<|LOC_994|>",
|
1000 |
+
"<|LOC_995|>",
|
1001 |
+
"<|LOC_996|>",
|
1002 |
+
"<|LOC_997|>",
|
1003 |
+
"<|LOC_998|>",
|
1004 |
+
"<|LOC_999|>",
|
1005 |
+
"<|LOC_1000|>",
|
1006 |
+
"<|LOC_BEGIN|>",
|
1007 |
+
"<|LOC_END|>",
|
1008 |
+
"<|LOC_SEP|>",
|
1009 |
+
"<|CROP_COL_SEP|>",
|
1010 |
+
"<|CROP_ROW_SEP|>",
|
1011 |
+
"<|IMAGE_SEP|>"
|
1012 |
+
],
|
1013 |
+
"bos_token": {
|
1014 |
+
"content": "<s>",
|
1015 |
+
"lstrip": false,
|
1016 |
+
"normalized": false,
|
1017 |
+
"rstrip": false,
|
1018 |
+
"single_word": false
|
1019 |
+
},
|
1020 |
+
"cls_token": {
|
1021 |
+
"content": "<|begin_of_sentence|>",
|
1022 |
+
"lstrip": false,
|
1023 |
+
"normalized": false,
|
1024 |
+
"rstrip": false,
|
1025 |
+
"single_word": false
|
1026 |
+
},
|
1027 |
+
"eos_token": {
|
1028 |
+
"content": "</s>",
|
1029 |
+
"lstrip": false,
|
1030 |
+
"normalized": false,
|
1031 |
+
"rstrip": false,
|
1032 |
+
"single_word": false
|
1033 |
+
},
|
1034 |
+
"mask_token": {
|
1035 |
+
"content": "<mask:1>",
|
1036 |
+
"lstrip": false,
|
1037 |
+
"normalized": false,
|
1038 |
+
"rstrip": false,
|
1039 |
+
"single_word": false
|
1040 |
+
},
|
1041 |
+
"pad_token": {
|
1042 |
+
"content": "<unk>",
|
1043 |
+
"lstrip": false,
|
1044 |
+
"normalized": false,
|
1045 |
+
"rstrip": false,
|
1046 |
+
"single_word": false
|
1047 |
+
},
|
1048 |
+
"sep_token": {
|
1049 |
+
"content": "<|end_of_sentence|>",
|
1050 |
+
"lstrip": false,
|
1051 |
+
"normalized": false,
|
1052 |
+
"rstrip": false,
|
1053 |
+
"single_word": false
|
1054 |
+
},
|
1055 |
+
"unk_token": {
|
1056 |
+
"content": "<unk>",
|
1057 |
+
"lstrip": false,
|
1058 |
+
"normalized": false,
|
1059 |
+
"rstrip": false,
|
1060 |
+
"single_word": false
|
1061 |
+
}
|
1062 |
+
}
|
test/tokenization_ernie4_5.py
ADDED
@@ -0,0 +1,373 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Copyright (c) 2025 Baidu, Inc. All Rights Reserved.
|
2 |
+
#
|
3 |
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
4 |
+
# you may not use this file except in compliance with the License.
|
5 |
+
# You may obtain a copy of the License at
|
6 |
+
#
|
7 |
+
# http://www.apache.org/licenses/LICENSE-2.0
|
8 |
+
#
|
9 |
+
# Unless required by applicable law or agreed to in writing, software
|
10 |
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
11 |
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
12 |
+
# See the License for the specific language governing permissions and
|
13 |
+
# limitations under the License.
|
14 |
+
|
15 |
+
import os
|
16 |
+
from shutil import copyfile
|
17 |
+
from typing import Dict, List, Optional, Tuple, Union
|
18 |
+
import torch
|
19 |
+
import numpy as np
|
20 |
+
import sentencepiece as spm
|
21 |
+
|
22 |
+
from transformers.tokenization_utils import PreTrainedTokenizer
|
23 |
+
from transformers.tokenization_utils_base import (
|
24 |
+
PaddingStrategy,
|
25 |
+
)
|
26 |
+
from transformers.utils import logging
|
27 |
+
|
28 |
+
|
29 |
+
logger = logging.get_logger(__name__)
|
30 |
+
|
31 |
+
|
32 |
+
class Ernie4_5_Tokenizer(PreTrainedTokenizer):
|
33 |
+
|
34 |
+
vocab_files_names = {
|
35 |
+
"vocab_file": "tokenizer.model",
|
36 |
+
}
|
37 |
+
# Model input names expected by the tokenizer
|
38 |
+
model_input_names = ["input_ids", "position_ids", "attention_mask", "labels"]
|
39 |
+
# Padding side (where to add padding tokens)
|
40 |
+
padding_side = "right"
|
41 |
+
|
42 |
+
def __init__(
|
43 |
+
self,
|
44 |
+
vocab_file,
|
45 |
+
bos_token="<s>",
|
46 |
+
cls_token="<cls>",
|
47 |
+
eos_token="</s>",
|
48 |
+
mask_token="<mask:0>",
|
49 |
+
pad_token="<pad>",
|
50 |
+
sep_token="<sep>",
|
51 |
+
unk_token="<unk>",
|
52 |
+
additional_special_tokens=None,
|
53 |
+
split_special_tokens=False,
|
54 |
+
tokenizer_alpha=None,
|
55 |
+
**kwargs,
|
56 |
+
):
|
57 |
+
"""
|
58 |
+
Initialize the ERNIE tokenizer.
|
59 |
+
|
60 |
+
Args:
|
61 |
+
vocab_file (str): Path to the SentencePiece model file.
|
62 |
+
bos_token (str, optional): Beginning of sentence token. Defaults to "<s>".
|
63 |
+
cls_token (str, optional): Classification token. Defaults to "<cls>".
|
64 |
+
eos_token (str, optional): End of sentence token. Defaults to "</s>".
|
65 |
+
mask_token (str, optional): Mask token. Defaults to "<mask:0>".
|
66 |
+
pad_token (str, optional): Padding token. Defaults to "<pad>".
|
67 |
+
sep_token (str, optional): Separator token. Defaults to "<sep>".
|
68 |
+
unk_token (str, optional): Unknown token. Defaults to "<unk>".
|
69 |
+
additional_special_tokens (List[str], optional): Additional special tokens.
|
70 |
+
Defaults to ["<mask:1>", "<mask:7>"].
|
71 |
+
split_special_tokens (bool, optional): Whether to split special tokens. Defaults to False.
|
72 |
+
tokenizer_alpha (float, optional): Alpha parameter for SentencePiece sampling.
|
73 |
+
**kwargs: Additional keyword arguments passed to the parent class.
|
74 |
+
"""
|
75 |
+
|
76 |
+
self.vocab_file = vocab_file
|
77 |
+
self.sp_model = spm.SentencePieceProcessor()
|
78 |
+
self.sp_model.Load(vocab_file)
|
79 |
+
self.tokenizer_alpha = tokenizer_alpha
|
80 |
+
|
81 |
+
if additional_special_tokens is None:
|
82 |
+
additional_special_tokens = ["<mask:1>", "<mask:7>"]
|
83 |
+
super().__init__(
|
84 |
+
bos_token=bos_token,
|
85 |
+
cls_token=cls_token,
|
86 |
+
eos_token=eos_token,
|
87 |
+
mask_token=mask_token,
|
88 |
+
pad_token=pad_token,
|
89 |
+
sep_token=sep_token,
|
90 |
+
unk_token=unk_token,
|
91 |
+
additional_special_tokens=additional_special_tokens,
|
92 |
+
split_special_tokens=split_special_tokens,
|
93 |
+
**kwargs,
|
94 |
+
)
|
95 |
+
|
96 |
+
@property
|
97 |
+
def vocab_size(self):
|
98 |
+
"""Returns the size of the vocabulary.
|
99 |
+
|
100 |
+
Returns:
|
101 |
+
int: The number of tokens in the vocabulary.
|
102 |
+
"""
|
103 |
+
return self.sp_model.vocab_size()
|
104 |
+
|
105 |
+
def get_vocab(self):
|
106 |
+
"""Get the vocabulary as a dictionary mapping tokens to their IDs.
|
107 |
+
|
108 |
+
Returns:
|
109 |
+
dict: A dictionary mapping tokens to their corresponding IDs.
|
110 |
+
"""
|
111 |
+
vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)}
|
112 |
+
vocab.update(self.added_tokens_encoder)
|
113 |
+
return vocab
|
114 |
+
|
115 |
+
def _tokenize(self, text):
|
116 |
+
"""Tokenize text using SentencePiece.
|
117 |
+
|
118 |
+
Args:
|
119 |
+
text (str): The text to tokenize.
|
120 |
+
|
121 |
+
Returns:
|
122 |
+
list: A list of tokens.
|
123 |
+
"""
|
124 |
+
if self.tokenizer_alpha is not None:
|
125 |
+
return self.sp_model.encode_as_pieces(
|
126 |
+
text,
|
127 |
+
enable_sampling=True,
|
128 |
+
nbest_size=-1,
|
129 |
+
alpha=self.tokenizer_alpha,
|
130 |
+
)
|
131 |
+
else:
|
132 |
+
return self.sp_model.encode_as_pieces(text)
|
133 |
+
|
134 |
+
def _convert_token_to_id(self, token):
|
135 |
+
"""Convert a token (str) to an ID using the vocabulary.
|
136 |
+
|
137 |
+
Args:
|
138 |
+
token (str): The token to convert.
|
139 |
+
|
140 |
+
Returns:
|
141 |
+
int: The corresponding token ID.
|
142 |
+
"""
|
143 |
+
return self.sp_model.piece_to_id(token)
|
144 |
+
|
145 |
+
def _convert_id_to_token(self, id):
|
146 |
+
"""Convert an ID to a token (str) using the vocabulary.
|
147 |
+
|
148 |
+
Args:
|
149 |
+
id (int): The token ID to convert.
|
150 |
+
|
151 |
+
Returns:
|
152 |
+
str: The corresponding token.
|
153 |
+
"""
|
154 |
+
if id >= self.vocab_size:
|
155 |
+
return self.unk_token
|
156 |
+
else:
|
157 |
+
return self.sp_model.id_to_piece(id)
|
158 |
+
|
159 |
+
def convert_tokens_to_string(self, tokens):
|
160 |
+
"""Convert a sequence of tokens back to a single string.
|
161 |
+
|
162 |
+
Args:
|
163 |
+
tokens (List[str]): A list of tokens to convert.
|
164 |
+
|
165 |
+
Returns:
|
166 |
+
str: The reconstructed string.
|
167 |
+
"""
|
168 |
+
current_sub_tokens = []
|
169 |
+
out_string = ""
|
170 |
+
prev_is_special = False
|
171 |
+
for token in tokens:
|
172 |
+
# make sure that special tokens are not decoded using sentencepiece model
|
173 |
+
if token in self.all_special_tokens:
|
174 |
+
if not prev_is_special:
|
175 |
+
out_string += " "
|
176 |
+
out_string += self.sp_model.decode(current_sub_tokens) + token
|
177 |
+
prev_is_special = True
|
178 |
+
current_sub_tokens = []
|
179 |
+
else:
|
180 |
+
current_sub_tokens.append(token)
|
181 |
+
prev_is_special = False
|
182 |
+
out_string += self.sp_model.decode(current_sub_tokens)
|
183 |
+
return out_string
|
184 |
+
|
185 |
+
def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
|
186 |
+
"""Build model inputs by adding special tokens to sequences.
|
187 |
+
|
188 |
+
Args:
|
189 |
+
token_ids_0 (List[int]): List of token IDs for the first sequence.
|
190 |
+
token_ids_1 (List[int], optional): List of token IDs for the second sequence.
|
191 |
+
|
192 |
+
Returns:
|
193 |
+
List[int]: List of token IDs with special tokens added.
|
194 |
+
"""
|
195 |
+
output = token_ids_0
|
196 |
+
last_cls_index = -1
|
197 |
+
last_sep_index = -1
|
198 |
+
if self.cls_token_id in output:
|
199 |
+
last_cls_index = len(output) - output[::-1].index(self.cls_token_id) - 1
|
200 |
+
if self.sep_token_id in output:
|
201 |
+
last_sep_index = len(output) - output[::-1].index(self.sep_token_id) - 1
|
202 |
+
|
203 |
+
if last_cls_index > last_sep_index:
|
204 |
+
next_token_id = self.sep_token_id
|
205 |
+
elif last_sep_index > last_cls_index:
|
206 |
+
next_token_id = self.cls_token_id
|
207 |
+
else:
|
208 |
+
output = [self.cls_token_id] + token_ids_0 + [self.sep_token_id]
|
209 |
+
next_token_id = self.cls_token_id
|
210 |
+
|
211 |
+
output = [self.bos_token_id] + output
|
212 |
+
# Assume no markup in text if token_ids_1 is given.
|
213 |
+
if token_ids_1 is not None:
|
214 |
+
output = output + token_ids_1 + [next_token_id]
|
215 |
+
return output
|
216 |
+
|
217 |
+
def get_special_tokens_mask(
|
218 |
+
self, token_ids_0, token_ids_1=None, already_has_special_tokens=False
|
219 |
+
):
|
220 |
+
"""Get a mask showing which tokens are special tokens.
|
221 |
+
|
222 |
+
Args:
|
223 |
+
token_ids_0 (List[int]): List of token IDs for the first sequence.
|
224 |
+
token_ids_1 (List[int], optional): List of token IDs for the second sequence.
|
225 |
+
already_has_special_tokens (bool): Whether the tokens already include special tokens.
|
226 |
+
|
227 |
+
Returns:
|
228 |
+
List[int]: A mask where 1 indicates special tokens and 0 indicates regular tokens.
|
229 |
+
"""
|
230 |
+
if already_has_special_tokens:
|
231 |
+
return super().get_special_tokens_mask(
|
232 |
+
token_ids_0, token_ids_1, already_has_special_tokens=True
|
233 |
+
)
|
234 |
+
|
235 |
+
# [bos_token, cls_token, tokens_0, sep_token]
|
236 |
+
if token_ids_1 is None:
|
237 |
+
return [1, 1] + ([0] * len(token_ids_0)) + [1]
|
238 |
+
# [bos_token, cls_token, tokens_0, sep_token, tokens_1, cls_token]
|
239 |
+
return [1, 1] + ([0] * len(token_ids_0)) + [1] + ([0] * len(token_ids_1)) + [1]
|
240 |
+
|
241 |
+
def save_vocabulary(
|
242 |
+
self, save_directory, filename_prefix: Optional[str] = None
|
243 |
+
) -> Tuple[str]:
|
244 |
+
"""
|
245 |
+
Save the vocabulary and special tokens file to a directory.
|
246 |
+
|
247 |
+
Args:
|
248 |
+
save_directory (str): The directory in which to save the vocabulary.
|
249 |
+
filename_prefix (Optional[str]): Optional prefix for the saved filename.
|
250 |
+
|
251 |
+
Returns:
|
252 |
+
Tuple[str]: Paths to the files saved.
|
253 |
+
|
254 |
+
Raises:
|
255 |
+
ValueError: If the save_directory is not a valid directory.
|
256 |
+
"""
|
257 |
+
if not os.path.isdir(save_directory):
|
258 |
+
logger.error(f"Vocabulary path ({save_directory}) should be a directory")
|
259 |
+
return
|
260 |
+
out_vocab_file = os.path.join(
|
261 |
+
save_directory,
|
262 |
+
(filename_prefix + "-" if filename_prefix else "")
|
263 |
+
+ self.vocab_files_names["vocab_file"],
|
264 |
+
)
|
265 |
+
|
266 |
+
if os.path.abspath(self.vocab_file) != os.path.abspath(
|
267 |
+
out_vocab_file
|
268 |
+
) and os.path.isfile(self.vocab_file):
|
269 |
+
copyfile(self.vocab_file, out_vocab_file)
|
270 |
+
elif not os.path.isfile(self.vocab_file):
|
271 |
+
with open(out_vocab_file, "wb") as fi:
|
272 |
+
content_spiece_model = self.sp_model.serialized_model_proto()
|
273 |
+
fi.write(content_spiece_model)
|
274 |
+
|
275 |
+
return (out_vocab_file,)
|
276 |
+
|
277 |
+
def _pad(
|
278 |
+
self,
|
279 |
+
encoded_inputs: Union[Dict],
|
280 |
+
max_length: Optional[int] = None,
|
281 |
+
padding_strategy: PaddingStrategy = PaddingStrategy.DO_NOT_PAD,
|
282 |
+
pad_to_multiple_of: Optional[int] = None,
|
283 |
+
padding_side: Optional[str] = None,
|
284 |
+
return_attention_mask: Optional[bool] = None,
|
285 |
+
) -> dict:
|
286 |
+
"""
|
287 |
+
Pad encoded inputs according to specified strategy.
|
288 |
+
|
289 |
+
Args:
|
290 |
+
encoded_inputs (Union[Dict]): Dictionary of encoded inputs.
|
291 |
+
max_length (Optional[int]): Maximum length to pad to.
|
292 |
+
padding_strategy (PaddingStrategy): Strategy for padding.
|
293 |
+
pad_to_multiple_of (Optional[int]): Pad to a multiple of this value.
|
294 |
+
return_attention_mask (Optional[bool]): Whether to return attention mask.
|
295 |
+
|
296 |
+
Returns:
|
297 |
+
dict: Dictionary with padded inputs and optional attention mask.
|
298 |
+
|
299 |
+
Raises:
|
300 |
+
ValueError: If attention_mask has unexpected type or invalid padding strategy.
|
301 |
+
"""
|
302 |
+
if return_attention_mask is None:
|
303 |
+
return_attention_mask = "attention_mask" in self.model_input_names
|
304 |
+
if return_attention_mask:
|
305 |
+
required_input = encoded_inputs[self.model_input_names[0]]
|
306 |
+
if padding_strategy == PaddingStrategy.LONGEST:
|
307 |
+
max_length = len(required_input)
|
308 |
+
if (
|
309 |
+
max_length is not None
|
310 |
+
and pad_to_multiple_of is not None
|
311 |
+
and (max_length % pad_to_multiple_of != 0)
|
312 |
+
):
|
313 |
+
max_length = (
|
314 |
+
(max_length // pad_to_multiple_of) + 1
|
315 |
+
) * pad_to_multiple_of
|
316 |
+
needs_to_be_padded = (
|
317 |
+
padding_strategy != PaddingStrategy.DO_NOT_PAD
|
318 |
+
and len(required_input) != max_length
|
319 |
+
)
|
320 |
+
|
321 |
+
if (
|
322 |
+
"attention_mask" in encoded_inputs
|
323 |
+
and encoded_inputs["attention_mask"] is not None
|
324 |
+
):
|
325 |
+
attention_mask = encoded_inputs.pop("attention_mask")
|
326 |
+
if isinstance(attention_mask, torch.Tensor):
|
327 |
+
attention_mask = attention_mask.numpy()
|
328 |
+
elif isinstance(attention_mask, list):
|
329 |
+
attention_mask = np.array(attention_mask)
|
330 |
+
elif not isinstance(attention_mask, np.ndarray):
|
331 |
+
raise ValueError(
|
332 |
+
f"Unexpected type {type(attention_mask)} of attention_mask, "
|
333 |
+
)
|
334 |
+
else:
|
335 |
+
# Create default attention mask if none provided
|
336 |
+
attention_mask = np.tril(
|
337 |
+
np.ones((len(required_input), len(required_input)), dtype=np.int64)
|
338 |
+
)
|
339 |
+
attention_mask = np.expand_dims(attention_mask, axis=0)
|
340 |
+
|
341 |
+
if needs_to_be_padded:
|
342 |
+
difference = max_length - len(required_input)
|
343 |
+
if self.padding_side == "right":
|
344 |
+
if attention_mask.ndim == 1:
|
345 |
+
pad_width = [(0, difference)]
|
346 |
+
else:
|
347 |
+
pad_width = [(0, 0), (0, difference), (0, difference)]
|
348 |
+
elif self.padding_side == "left":
|
349 |
+
if attention_mask.ndim == 1:
|
350 |
+
pad_width = [(difference, 0)]
|
351 |
+
else:
|
352 |
+
pad_width = [(0, 0), (difference, 0), (difference, 0)]
|
353 |
+
else:
|
354 |
+
raise ValueError(
|
355 |
+
"Invalid padding strategy:" + str(self.padding_side)
|
356 |
+
)
|
357 |
+
attention_mask = np.pad(
|
358 |
+
attention_mask,
|
359 |
+
pad_width=pad_width,
|
360 |
+
mode="constant",
|
361 |
+
constant_values=0,
|
362 |
+
)
|
363 |
+
|
364 |
+
encoded_inputs = super()._pad(
|
365 |
+
encoded_inputs,
|
366 |
+
max_length,
|
367 |
+
padding_strategy=padding_strategy,
|
368 |
+
pad_to_multiple_of=pad_to_multiple_of,
|
369 |
+
return_attention_mask=False,
|
370 |
+
)
|
371 |
+
if return_attention_mask:
|
372 |
+
encoded_inputs["attention_mask"] = attention_mask.tolist()
|
373 |
+
return encoded_inputs
|
test/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34ef7db83df785924fb83d7b887b6e822a031c56e15cff40aaf9b982988180df
|
3 |
+
size 1614363
|
test/tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e7319db963d73e25ca045737fdba526d52fdbb71fca0d83d1953e322a3dbdd5
|
3 |
+
size 2379098
|
tokenizer_config.json
CHANGED
@@ -1,7 +1,4 @@
|
|
1 |
{
|
2 |
-
"add_bos_token": true,
|
3 |
-
"add_eos_token": false,
|
4 |
-
"add_prefix_space": true,
|
5 |
"added_tokens_decoder": {
|
6 |
"0": {
|
7 |
"content": "<unk>",
|
@@ -27,86 +24,6 @@
|
|
27 |
"single_word": false,
|
28 |
"special": true
|
29 |
},
|
30 |
-
"3": {
|
31 |
-
"content": "0",
|
32 |
-
"lstrip": false,
|
33 |
-
"normalized": false,
|
34 |
-
"rstrip": false,
|
35 |
-
"single_word": false,
|
36 |
-
"special": false
|
37 |
-
},
|
38 |
-
"4": {
|
39 |
-
"content": "1",
|
40 |
-
"lstrip": false,
|
41 |
-
"normalized": false,
|
42 |
-
"rstrip": false,
|
43 |
-
"single_word": false,
|
44 |
-
"special": false
|
45 |
-
},
|
46 |
-
"5": {
|
47 |
-
"content": "2",
|
48 |
-
"lstrip": false,
|
49 |
-
"normalized": false,
|
50 |
-
"rstrip": false,
|
51 |
-
"single_word": false,
|
52 |
-
"special": false
|
53 |
-
},
|
54 |
-
"6": {
|
55 |
-
"content": "3",
|
56 |
-
"lstrip": false,
|
57 |
-
"normalized": false,
|
58 |
-
"rstrip": false,
|
59 |
-
"single_word": false,
|
60 |
-
"special": false
|
61 |
-
},
|
62 |
-
"7": {
|
63 |
-
"content": "4",
|
64 |
-
"lstrip": false,
|
65 |
-
"normalized": false,
|
66 |
-
"rstrip": false,
|
67 |
-
"single_word": false,
|
68 |
-
"special": false
|
69 |
-
},
|
70 |
-
"8": {
|
71 |
-
"content": "5",
|
72 |
-
"lstrip": false,
|
73 |
-
"normalized": false,
|
74 |
-
"rstrip": false,
|
75 |
-
"single_word": false,
|
76 |
-
"special": false
|
77 |
-
},
|
78 |
-
"9": {
|
79 |
-
"content": "6",
|
80 |
-
"lstrip": false,
|
81 |
-
"normalized": false,
|
82 |
-
"rstrip": false,
|
83 |
-
"single_word": false,
|
84 |
-
"special": false
|
85 |
-
},
|
86 |
-
"10": {
|
87 |
-
"content": "7",
|
88 |
-
"lstrip": false,
|
89 |
-
"normalized": false,
|
90 |
-
"rstrip": false,
|
91 |
-
"single_word": false,
|
92 |
-
"special": false
|
93 |
-
},
|
94 |
-
"11": {
|
95 |
-
"content": "8",
|
96 |
-
"lstrip": false,
|
97 |
-
"normalized": false,
|
98 |
-
"rstrip": false,
|
99 |
-
"single_word": false,
|
100 |
-
"special": false
|
101 |
-
},
|
102 |
-
"12": {
|
103 |
-
"content": "9",
|
104 |
-
"lstrip": false,
|
105 |
-
"normalized": false,
|
106 |
-
"rstrip": false,
|
107 |
-
"single_word": false,
|
108 |
-
"special": false
|
109 |
-
},
|
110 |
"100272": {
|
111 |
"content": "<|end_of_sentence|>",
|
112 |
"lstrip": false,
|
@@ -9217,29 +9134,24 @@
|
|
9217 |
],
|
9218 |
"auto_map": {
|
9219 |
"AutoTokenizer": [
|
9220 |
-
"
|
9221 |
null
|
9222 |
]
|
9223 |
},
|
9224 |
"bos_token": "<s>",
|
9225 |
-
"chat_template": "{%- if not add_generation_prompt is defined -%}\n {%- set add_generation_prompt = true -%}\n{%- endif -%}\n{%- if not cls_token is defined -%}\n {%- set cls_token = \"<|begin_of_sentence|>\" -%}\n{%- endif -%}\n{%- if not sep_token is defined -%}\n {%- set sep_token = \"<|end_of_sentence|>\" -%}\n{%- endif -%}\n{{- cls_token -}}\n{%- for message in messages -%}\n {%- if message[\"role\"] == \"user\" -%}\n {{- \"User: \" + message[\"content\"] + \"\n\" -}}\n {%- elif message[\"role\"] == \"assistant\" -%}\n {{- \"Assistant: \" + message[\"content\"] + sep_token -}}\n {%- elif message[\"role\"] == \"system\" -%}\n {{- message[\"content\"] + \"\n\" -}}\n {%- endif -%}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{- \"Assistant: \" -}}\n{%- endif -%}",
|
9226 |
"clean_up_tokenization_spaces": false,
|
9227 |
"cls_token": "<|begin_of_sentence|>",
|
9228 |
"eos_token": "</s>",
|
9229 |
"extra_special_tokens": {},
|
9230 |
"header_end_token": "<mask:7>",
|
9231 |
"header_start_token": "<mask:6>",
|
9232 |
-
"legacy": false,
|
9233 |
"mask_token": "<mask:1>",
|
9234 |
"model_max_length": 1000000000000000019884624838656,
|
9235 |
"pad_token": "<unk>",
|
9236 |
"sep_token": "<|end_of_sentence|>",
|
9237 |
-
"sp_model_kwargs": {},
|
9238 |
-
"spaces_between_special_tokens": false,
|
9239 |
"split_special_tokens": false,
|
9240 |
"sys_end_token": "<mask:5>",
|
9241 |
"sys_start_token": "<mask:4>",
|
9242 |
-
"tokenizer_class": "
|
9243 |
-
"unk_token": "<unk>"
|
9244 |
-
"use_default_system_prompt": false
|
9245 |
}
|
|
|
1 |
{
|
|
|
|
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
"content": "<unk>",
|
|
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
27 |
"100272": {
|
28 |
"content": "<|end_of_sentence|>",
|
29 |
"lstrip": false,
|
|
|
9134 |
],
|
9135 |
"auto_map": {
|
9136 |
"AutoTokenizer": [
|
9137 |
+
"tokenization_ernie4_5.Ernie4_5_Tokenizer",
|
9138 |
null
|
9139 |
]
|
9140 |
},
|
9141 |
"bos_token": "<s>",
|
|
|
9142 |
"clean_up_tokenization_spaces": false,
|
9143 |
"cls_token": "<|begin_of_sentence|>",
|
9144 |
"eos_token": "</s>",
|
9145 |
"extra_special_tokens": {},
|
9146 |
"header_end_token": "<mask:7>",
|
9147 |
"header_start_token": "<mask:6>",
|
|
|
9148 |
"mask_token": "<mask:1>",
|
9149 |
"model_max_length": 1000000000000000019884624838656,
|
9150 |
"pad_token": "<unk>",
|
9151 |
"sep_token": "<|end_of_sentence|>",
|
|
|
|
|
9152 |
"split_special_tokens": false,
|
9153 |
"sys_end_token": "<mask:5>",
|
9154 |
"sys_start_token": "<mask:4>",
|
9155 |
+
"tokenizer_class": "Ernie4_5_Tokenizer",
|
9156 |
+
"unk_token": "<unk>"
|
|
|
9157 |
}
|