hadifar commited on
Commit
75fd719
1 Parent(s): 09d5908

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +42 -6
  2. tokenizer.json +4 -4
  3. tokenizer_config.json +46 -0
special_tokens_map.json CHANGED
@@ -1,7 +1,25 @@
1
  {
2
- "bos_token": "<s>",
3
- "cls_token": "<s>",
4
- "eos_token": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "mask_token": {
6
  "content": "<mask>",
7
  "lstrip": true,
@@ -9,7 +27,25 @@
9
  "rstrip": false,
10
  "single_word": false
11
  },
12
- "pad_token": "<pad>",
13
- "sep_token": "</s>",
14
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
  "mask_token": {
24
  "content": "<mask>",
25
  "lstrip": 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": "</s>",
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 CHANGED
@@ -14,7 +14,7 @@
14
  "single_word": false,
15
  "lstrip": false,
16
  "rstrip": false,
17
- "normalized": false,
18
  "special": true
19
  },
20
  {
@@ -23,7 +23,7 @@
23
  "single_word": false,
24
  "lstrip": false,
25
  "rstrip": false,
26
- "normalized": false,
27
  "special": true
28
  },
29
  {
@@ -32,7 +32,7 @@
32
  "single_word": false,
33
  "lstrip": false,
34
  "rstrip": false,
35
- "normalized": false,
36
  "special": true
37
  },
38
  {
@@ -41,7 +41,7 @@
41
  "single_word": false,
42
  "lstrip": false,
43
  "rstrip": false,
44
- "normalized": false,
45
  "special": true
46
  },
47
  {
 
14
  "single_word": false,
15
  "lstrip": false,
16
  "rstrip": false,
17
+ "normalized": true,
18
  "special": true
19
  },
20
  {
 
23
  "single_word": false,
24
  "lstrip": false,
25
  "rstrip": false,
26
+ "normalized": true,
27
  "special": true
28
  },
29
  {
 
32
  "single_word": false,
33
  "lstrip": false,
34
  "rstrip": false,
35
+ "normalized": true,
36
  "special": true
37
  },
38
  {
 
41
  "single_word": false,
42
  "lstrip": false,
43
  "rstrip": false,
44
+ "normalized": true,
45
  "special": true
46
  },
47
  {
tokenizer_config.json CHANGED
@@ -1,15 +1,61 @@
1
  {
2
  "add_prefix_space": false,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "bos_token": "<s>",
4
  "clean_up_tokenization_spaces": true,
5
  "cls_token": "<s>",
6
  "eos_token": "</s>",
7
  "errors": "replace",
8
  "mask_token": "<mask>",
 
9
  "model_max_length": 512,
10
  "pad_token": "<pad>",
11
  "sep_token": "</s>",
 
12
  "tokenizer_class": "RobertaTokenizer",
13
  "trim_offsets": true,
 
 
14
  "unk_token": "<unk>"
15
  }
 
1
  {
2
  "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
  "bos_token": "<s>",
46
  "clean_up_tokenization_spaces": true,
47
  "cls_token": "<s>",
48
  "eos_token": "</s>",
49
  "errors": "replace",
50
  "mask_token": "<mask>",
51
+ "max_length": 512,
52
  "model_max_length": 512,
53
  "pad_token": "<pad>",
54
  "sep_token": "</s>",
55
+ "stride": 0,
56
  "tokenizer_class": "RobertaTokenizer",
57
  "trim_offsets": true,
58
+ "truncation_side": "right",
59
+ "truncation_strategy": "longest_first",
60
  "unk_token": "<unk>"
61
  }