junejae commited on
Commit
ed28aa0
โ€ข
1 Parent(s): 2ac86bc

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +35 -5
  2. tokenizer.json +16 -16
  3. vocab.txt +16 -16
special_tokens_map.json CHANGED
@@ -1,7 +1,37 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
 
1
  {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
  }
tokenizer.json CHANGED
@@ -150,22 +150,22 @@
150
  "[CLS]": 2,
151
  "[SEP]": 3,
152
  "[MASK]": 4,
153
- "[unused0]": 5,
154
- "[unused1]": 6,
155
- "[unused2]": 7,
156
- "[unused3]": 8,
157
- "[unused4]": 9,
158
- "[unused5]": 10,
159
- "[unused6]": 11,
160
- "[unused7]": 12,
161
- "[unused8]": 13,
162
- "[unused9]": 14,
163
- "[unused10]": 15,
164
- "[unused11]": 16,
165
- "[unused12]": 17,
166
- "[unused13]": 18,
167
- "[unused14]": 19,
168
- "[unused15]": 20,
169
  "[unused16]": 21,
170
  "[unused17]": 22,
171
  "[unused18]": 23,
 
150
  "[CLS]": 2,
151
  "[SEP]": 3,
152
  "[MASK]": 4,
153
+ "์žฌํƒ": 5,
154
+ "๋ฌด๋“œ๋“ฑ": 6,
155
+ "๋‹ค์šฉ๋„์‹ค": 7,
156
+ "์œ„์ธต": 8,
157
+ "์ „๋“ฑ": 9,
158
+ "ํŒŒ๋ž—๊ฒŒ": 10,
159
+ "์ ์ƒ‰": 11,
160
+ "๋…ธ๋ž—๊ฒŒ": 12,
161
+ "๋„๋ก": 13,
162
+ "๋‚ฎ์ถœ": 14,
163
+ "ํ•ด์ฃผ์‹ค": 15,
164
+ "ํ™•์ธํ•ด๋ณผ": 16,
165
+ "์•Œ๋ ค์ค„": 17,
166
+ "๋‹ค๋ฝ๋ฐฉ": 18,
167
+ "์ž‘์€๋ฐฉ": 19,
168
+ "ํฐ๋ฐฉ": 20,
169
  "[unused16]": 21,
170
  "[unused17]": 22,
171
  "[unused18]": 23,
vocab.txt CHANGED
@@ -3,22 +3,22 @@
3
  [CLS]
4
  [SEP]
5
  [MASK]
6
- [unused0]
7
- [unused1]
8
- [unused2]
9
- [unused3]
10
- [unused4]
11
- [unused5]
12
- [unused6]
13
- [unused7]
14
- [unused8]
15
- [unused9]
16
- [unused10]
17
- [unused11]
18
- [unused12]
19
- [unused13]
20
- [unused14]
21
- [unused15]
22
  [unused16]
23
  [unused17]
24
  [unused18]
 
3
  [CLS]
4
  [SEP]
5
  [MASK]
6
+ ์žฌํƒ
7
+ ๋ฌด๋“œ๋“ฑ
8
+ ๋‹ค์šฉ๋„์‹ค
9
+ ์œ„์ธต
10
+ ์ „๋“ฑ
11
+ ํŒŒ๋ž—๊ฒŒ
12
+ ์ ์ƒ‰
13
+ ๋…ธ๋ž—๊ฒŒ
14
+ ๋„๋ก
15
+ ๋‚ฎ์ถœ
16
+ ํ•ด์ฃผ์‹ค
17
+ ํ™•์ธํ•ด๋ณผ
18
+ ์•Œ๋ ค์ค„
19
+ ๋‹ค๋ฝ๋ฐฉ
20
+ ์ž‘์€๋ฐฉ
21
+ ํฐ๋ฐฉ
22
  [unused16]
23
  [unused17]
24
  [unused18]