HuyenNguyen
commited on
Commit
•
3f5bee9
1
Parent(s):
cf5865a
Upload tokenizer
Browse files- added_tokens.json +2 -2
- special_tokens_map.json +0 -16
- tokenizer_config.json +34 -0
- vocab.json +64 -66
added_tokens.json
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
{
|
2 |
-
"</s>":
|
3 |
-
"<s>":
|
4 |
}
|
|
|
1 |
{
|
2 |
+
"</s>": 90,
|
3 |
+
"<s>": 89
|
4 |
}
|
special_tokens_map.json
CHANGED
@@ -1,20 +1,4 @@
|
|
1 |
{
|
2 |
-
"additional_special_tokens": [
|
3 |
-
{
|
4 |
-
"content": "<s>",
|
5 |
-
"lstrip": false,
|
6 |
-
"normalized": true,
|
7 |
-
"rstrip": false,
|
8 |
-
"single_word": false
|
9 |
-
},
|
10 |
-
{
|
11 |
-
"content": "</s>",
|
12 |
-
"lstrip": false,
|
13 |
-
"normalized": true,
|
14 |
-
"rstrip": false,
|
15 |
-
"single_word": false
|
16 |
-
}
|
17 |
-
],
|
18 |
"bos_token": "<s>",
|
19 |
"eos_token": "</s>",
|
20 |
"pad_token": "[PAD]",
|
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": "<s>",
|
3 |
"eos_token": "</s>",
|
4 |
"pad_token": "[PAD]",
|
tokenizer_config.json
CHANGED
@@ -1,4 +1,38 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": "<s>",
|
3 |
"clean_up_tokenization_spaces": true,
|
4 |
"do_lower_case": false,
|
|
|
1 |
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"87": {
|
4 |
+
"content": "[UNK]",
|
5 |
+
"lstrip": true,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": true,
|
8 |
+
"single_word": false,
|
9 |
+
"special": false
|
10 |
+
},
|
11 |
+
"88": {
|
12 |
+
"content": "[PAD]",
|
13 |
+
"lstrip": true,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": true,
|
16 |
+
"single_word": false,
|
17 |
+
"special": false
|
18 |
+
},
|
19 |
+
"89": {
|
20 |
+
"content": "<s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": true,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"90": {
|
28 |
+
"content": "</s>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
}
|
35 |
+
},
|
36 |
"bos_token": "<s>",
|
37 |
"clean_up_tokenization_spaces": true,
|
38 |
"do_lower_case": false,
|
vocab.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"vi": {
|
3 |
-
"[PAD]":
|
4 |
-
"[UNK]":
|
5 |
"a": 1,
|
6 |
"b": 2,
|
7 |
"c": 3,
|
@@ -27,69 +27,67 @@
|
|
27 |
"|": 0,
|
28 |
"à": 23,
|
29 |
"á": 24,
|
30 |
-
"
|
31 |
-
"
|
32 |
-
"
|
33 |
-
"
|
34 |
-
"
|
35 |
-
"
|
36 |
-
"
|
37 |
-
"
|
38 |
-
"
|
39 |
-
"
|
40 |
-
"
|
41 |
-
"
|
42 |
-
"
|
43 |
-
"
|
44 |
-
"
|
45 |
-
"
|
46 |
-
"
|
47 |
-
"
|
48 |
-
"
|
49 |
-
"
|
50 |
-
"
|
51 |
-
"
|
52 |
-
"
|
53 |
-
"
|
54 |
-
"
|
55 |
-
"
|
56 |
-
"
|
57 |
-
"
|
58 |
-
"
|
59 |
-
"
|
60 |
-
"
|
61 |
-
"
|
62 |
-
"
|
63 |
-
"
|
64 |
-
"
|
65 |
-
"
|
66 |
-
"
|
67 |
-
"
|
68 |
-
"
|
69 |
-
"
|
70 |
-
"
|
71 |
-
"
|
72 |
-
"
|
73 |
-
"
|
74 |
-
"
|
75 |
-
"
|
76 |
-
"
|
77 |
-
"
|
78 |
-
"
|
79 |
-
"
|
80 |
-
"
|
81 |
-
"
|
82 |
-
"
|
83 |
-
"
|
84 |
-
"
|
85 |
-
"
|
86 |
-
"
|
87 |
-
"
|
88 |
-
"
|
89 |
-
"
|
90 |
-
"
|
91 |
-
"
|
92 |
-
"ỷ": 87,
|
93 |
-
"ỹ": 88
|
94 |
}
|
95 |
}
|
|
|
1 |
{
|
2 |
"vi": {
|
3 |
+
"[PAD]": 88,
|
4 |
+
"[UNK]": 87,
|
5 |
"a": 1,
|
6 |
"b": 2,
|
7 |
"c": 3,
|
|
|
27 |
"|": 0,
|
28 |
"à": 23,
|
29 |
"á": 24,
|
30 |
+
"ã": 25,
|
31 |
+
"è": 26,
|
32 |
+
"é": 27,
|
33 |
+
"ê": 28,
|
34 |
+
"ì": 29,
|
35 |
+
"í": 30,
|
36 |
+
"ò": 31,
|
37 |
+
"ó": 32,
|
38 |
+
"õ": 33,
|
39 |
+
"ù": 34,
|
40 |
+
"ú": 35,
|
41 |
+
"ý": 36,
|
42 |
+
"ă": 37,
|
43 |
+
"đ": 38,
|
44 |
+
"ĩ": 39,
|
45 |
+
"ũ": 40,
|
46 |
+
"ơ": 41,
|
47 |
+
"ư": 42,
|
48 |
+
"ạ": 43,
|
49 |
+
"ả": 44,
|
50 |
+
"ấ": 45,
|
51 |
+
"ầ": 46,
|
52 |
+
"ẩ": 47,
|
53 |
+
"ẫ": 48,
|
54 |
+
"ậ": 49,
|
55 |
+
"ắ": 50,
|
56 |
+
"ằ": 51,
|
57 |
+
"ẳ": 52,
|
58 |
+
"ẵ": 53,
|
59 |
+
"ặ": 54,
|
60 |
+
"ẹ": 55,
|
61 |
+
"ẻ": 56,
|
62 |
+
"ẽ": 57,
|
63 |
+
"ế": 58,
|
64 |
+
"ề": 59,
|
65 |
+
"ể": 60,
|
66 |
+
"ễ": 61,
|
67 |
+
"ệ": 62,
|
68 |
+
"ỉ": 63,
|
69 |
+
"ị": 64,
|
70 |
+
"ọ": 65,
|
71 |
+
"ỏ": 66,
|
72 |
+
"ố": 67,
|
73 |
+
"ồ": 68,
|
74 |
+
"ổ": 69,
|
75 |
+
"ỗ": 70,
|
76 |
+
"ộ": 71,
|
77 |
+
"ớ": 72,
|
78 |
+
"ờ": 73,
|
79 |
+
"ở": 74,
|
80 |
+
"ỡ": 75,
|
81 |
+
"ợ": 76,
|
82 |
+
"ụ": 77,
|
83 |
+
"ủ": 78,
|
84 |
+
"ứ": 79,
|
85 |
+
"ừ": 80,
|
86 |
+
"ử": 81,
|
87 |
+
"ữ": 82,
|
88 |
+
"ự": 83,
|
89 |
+
"ỳ": 84,
|
90 |
+
"ỷ": 85,
|
91 |
+
"ỹ": 86
|
|
|
|
|
92 |
}
|
93 |
}
|