MrAnderson commited on
Commit
bc3c3fc
1 Parent(s): 7422752

add tokenizer

Browse files
Files changed (5) hide show
  1. merges.txt +0 -0
  2. special_tokens_map.json +51 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +67 -0
  5. vocab.json +0 -0
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "[CLS]",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "cls_token": {
13
+ "__type": "AddedToken",
14
+ "content": "[CLS]",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "do_lower_case": false,
21
+ "eos_token": {
22
+ "__type": "AddedToken",
23
+ "content": "[SEP]",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ },
29
+ "errors": "replace",
30
+ "mask_token": {
31
+ "__type": "AddedToken",
32
+ "content": "[MASK]",
33
+ "lstrip": true,
34
+ "normalized": true,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ "model_max_length": 512,
39
+ "name_or_path": "microsoft/deberta-base",
40
+ "pad_token": {
41
+ "__type": "AddedToken",
42
+ "content": "[PAD]",
43
+ "lstrip": false,
44
+ "normalized": true,
45
+ "rstrip": false,
46
+ "single_word": false
47
+ },
48
+ "sep_token": {
49
+ "__type": "AddedToken",
50
+ "content": "[SEP]",
51
+ "lstrip": false,
52
+ "normalized": true,
53
+ "rstrip": false,
54
+ "single_word": false
55
+ },
56
+ "special_tokens_map_file": null,
57
+ "tokenizer_class": "DebertaTokenizer",
58
+ "unk_token": {
59
+ "__type": "AddedToken",
60
+ "content": "[UNK]",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ "vocab_type": "gpt2"
67
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff