renwei2024 commited on
Commit
59174bb
·
verified ·
1 Parent(s): 42b8b9a

Upload tokenizer

Browse files
Files changed (3) hide show
  1. tokenizer.json +0 -0
  2. tokenizer_config.json +8 -8
  3. vocab.txt +0 -0
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,22 +1,22 @@
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
- "content": "[PAD]",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
10
  },
11
- "100": {
12
- "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
- "101": {
20
  "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "102": {
28
  "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
@@ -32,7 +32,7 @@
32
  "single_word": false,
33
  "special": true
34
  },
35
- "103": {
36
  "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
@@ -43,10 +43,10 @@
43
  },
44
  "clean_up_tokenization_spaces": false,
45
  "cls_token": "[CLS]",
46
- "do_lower_case": false,
47
  "extra_special_tokens": {},
48
  "mask_token": "[MASK]",
49
- "model_max_length": 512,
50
  "pad_token": "[PAD]",
51
  "sep_token": "[SEP]",
52
  "strip_accents": null,
 
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
+ "content": "[UNK]",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
10
  },
11
+ "1": {
12
+ "content": "[PAD]",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
+ "2": {
20
  "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "3": {
28
  "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
 
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "4": {
36
  "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
 
43
  },
44
  "clean_up_tokenization_spaces": false,
45
  "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
  "extra_special_tokens": {},
48
  "mask_token": "[MASK]",
49
+ "model_max_length": 1000000000000000019884624838656,
50
  "pad_token": "[PAD]",
51
  "sep_token": "[SEP]",
52
  "strip_accents": null,
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff