Armin Mehrabian commited on
Commit
8b99bac
1 Parent(s): f0b40e6

tokenizer confige and special tokens updated.

Browse files
added_tokens.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "[CLS]": 101,
3
- "[MASK]": 103,
4
- "[PAD]": 0,
5
- "[SEP]": 102,
6
- "[UNK]": 100
7
  }
 
1
  {
2
+ "</s>": 2,
3
+ "<mask>": 50264,
4
+ "<pad>": 1,
5
+ "<s>": 0,
6
+ "<unk>": 3
7
  }
special_tokens_map.json CHANGED
@@ -1,7 +1,9 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
7
  }
 
1
  {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
+ "pad_token": "<pad>",
7
+ "sep_token": "</s>",
8
+ "unk_token": "<unk>"
9
  }
tokenizer_config.json CHANGED
@@ -1,40 +1,41 @@
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,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
27
- "102": {
28
- "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
- "103": {
36
- "content": "[MASK]",
37
- "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
@@ -42,15 +43,20 @@
42
  }
43
  },
44
  "additional_special_tokens": [],
 
45
  "clean_up_tokenization_spaces": true,
46
- "cls_token": "[CLS]",
47
- "do_lower_case": true,
48
- "mask_token": "[MASK]",
49
- "model_max_length": 512,
50
- "pad_token": "[PAD]",
51
- "sep_token": "[SEP]",
52
- "strip_accents": null,
53
- "tokenize_chinese_chars": true,
54
- "tokenizer_class": "BertTokenizer",
55
- "unk_token": "[UNK]"
 
 
 
 
56
  }
 
1
  {
2
+ "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
  "0": {
5
+ "content": "<s>",
6
  "lstrip": false,
7
  "normalized": false,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  },
12
+ "1": {
13
+ "content": "<pad>",
14
  "lstrip": false,
15
  "normalized": false,
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
19
  },
20
+ "2": {
21
+ "content": "</s>",
22
  "lstrip": false,
23
  "normalized": false,
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
27
  },
28
+ "3": {
29
+ "content": "<unk>",
30
  "lstrip": false,
31
  "normalized": false,
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,
 
43
  }
44
  },
45
  "additional_special_tokens": [],
46
+ "bos_token": "<s>",
47
  "clean_up_tokenization_spaces": true,
48
+ "cls_token": "<s>",
49
+ "eos_token": "</s>",
50
+ "errors": "replace",
51
+ "mask_token": "<mask>",
52
+ "max_length": 256,
53
+ "model_max_length": 1000000000000000019884624838656,
54
+ "pad_token": "<pad>",
55
+ "sep_token": "</s>",
56
+ "stride": 0,
57
+ "tokenizer_class": "RobertaTokenizer",
58
+ "trim_offsets": true,
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
+ "unk_token": "<unk>"
62
  }
vocab.json ADDED
The diff for this file is too large to render. See raw diff