Create tokenizer.json
Browse files- tokenizer.json +107 -0
tokenizer.json
ADDED
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "0.1",
|
3 |
+
"truncation": {
|
4 |
+
"max_length": 512,
|
5 |
+
"stride": 0,
|
6 |
+
"strategy": "longest_first"
|
7 |
+
},
|
8 |
+
"padding": {
|
9 |
+
"strategy": "longest",
|
10 |
+
"max_length": 512,
|
11 |
+
"pad_to_multiple_of": null
|
12 |
+
},
|
13 |
+
"added_tokens": [
|
14 |
+
{
|
15 |
+
"id": 0,
|
16 |
+
"content": "[PAD]",
|
17 |
+
"single_word": false,
|
18 |
+
"lstrip": false,
|
19 |
+
"rstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"special": true
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"id": 1,
|
25 |
+
"content": "[UNK]",
|
26 |
+
"single_word": false,
|
27 |
+
"lstrip": false,
|
28 |
+
"rstrip": false,
|
29 |
+
"normalized": false,
|
30 |
+
"special": true
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"id": 2,
|
34 |
+
"content": "[CLS]",
|
35 |
+
"single_word": false,
|
36 |
+
"lstrip": false,
|
37 |
+
"rstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"special": true
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"id": 3,
|
43 |
+
"content": "[SEP]",
|
44 |
+
"single_word": false,
|
45 |
+
"lstrip": false,
|
46 |
+
"rstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"special": true
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"id": 4,
|
52 |
+
"content": "[MASK]",
|
53 |
+
"single_word": false,
|
54 |
+
"lstrip": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"special": true
|
58 |
+
}
|
59 |
+
],
|
60 |
+
"normalizer": {
|
61 |
+
"type": "BertNormalizer",
|
62 |
+
"clean_text": true,
|
63 |
+
"handle_chinese_chars": true,
|
64 |
+
"strip_accents": null,
|
65 |
+
"lowercase": false
|
66 |
+
},
|
67 |
+
"pre_tokenizer": {
|
68 |
+
"type": "BertPreTokenizer"
|
69 |
+
},
|
70 |
+
"post_processor": {
|
71 |
+
"type": "BertPostProcessor",
|
72 |
+
"sep": {
|
73 |
+
"type": "AddedToken",
|
74 |
+
"content": "[SEP]",
|
75 |
+
"single_word": false,
|
76 |
+
"lstrip": false,
|
77 |
+
"rstrip": false,
|
78 |
+
"normalized": false
|
79 |
+
},
|
80 |
+
"cls": {
|
81 |
+
"type": "AddedToken",
|
82 |
+
"content": "[CLS]",
|
83 |
+
"single_word": false,
|
84 |
+
"lstrip": false,
|
85 |
+
"rstrip": false,
|
86 |
+
"normalized": false
|
87 |
+
}
|
88 |
+
},
|
89 |
+
"decoder": {
|
90 |
+
"type": "WordPiece",
|
91 |
+
"cleanup": true
|
92 |
+
},
|
93 |
+
"model": {
|
94 |
+
"type": "WordPiece",
|
95 |
+
"unk_token": "[UNK]",
|
96 |
+
"vocab": {
|
97 |
+
"[PAD]": 0,
|
98 |
+
"[UNK]": 1,
|
99 |
+
"[CLS]": 2,
|
100 |
+
"[SEP]": 3,
|
101 |
+
"[MASK]": 4,
|
102 |
+
"hello": 5,
|
103 |
+
"world": 6
|
104 |
+
},
|
105 |
+
"max_input_chars_per_word": 100
|
106 |
+
}
|
107 |
+
}
|