Hugging Face's logo

EuropeanParliament
/
EUBERT

Fill-Mask
Transformers
PyTorch
Safetensors
24 languages
roberta
generated_from_trainer
Inference Endpoints
Model card Files Community
4
scampion commited on
Commit
cc82d33
•
1 Parent(s): 3ac748f

Upload tokenizer

Browse files
Files changed (5) hide show
  1. added_tokens.json +12 -0
  2. special_tokens_map.json +19 -49
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +100 -55
  5. vocab.txt +0 -0
added_tokens.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 65537,
3
+ "<mask>": 65540,
4
+ "<pad>": 65539,
5
+ "<s>": 65536,
6
+ "<unk>": 65538,
7
+ "[CLS]": 2,
8
+ "[MASK]": 4,
9
+ "[PAD]": 1,
10
+ "[SEP]": 3,
11
+ "[UNK]": 0
12
+ }
special_tokens_map.json CHANGED
@@ -1,51 +1,21 @@
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,
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": "</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
  }
 
1
  {
2
+ "additional_special_tokens": [
3
+ "[UNK]",
4
+ "[PAD]",
5
+ "[CLS]",
6
+ "[SEP]",
7
+ "[MASK]",
8
+ "<s>",
9
+ "</s>",
10
+ "<unk>",
11
+ "<pad>",
12
+ "<mask>"
13
+ ],
14
+ "bos_token": "[CLS]",
15
+ "cls_token": "[CLS]",
16
+ "eos_token": "[SEP]",
17
+ "mask_token": "[MASK]",
18
+ "pad_token": "[PAD]",
19
+ "sep_token": "[SEP]",
20
+ "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,65 +1,110 @@
1
  {
2
  "add_prefix_space": false,
3
- "bos_token": {
4
- "__type": "AddedToken",
5
- "content": "<s>",
6
- "lstrip": false,
7
- "normalized": true,
8
- "rstrip": false,
9
- "single_word": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  "clean_up_tokenization_spaces": true,
12
- "cls_token": {
13
- "__type": "AddedToken",
14
- "content": "<s>",
15
- "lstrip": false,
16
- "normalized": true,
17
- "rstrip": false,
18
- "single_word": false
19
- },
20
- "eos_token": {
21
- "__type": "AddedToken",
22
- "content": "</s>",
23
- "lstrip": false,
24
- "normalized": true,
25
- "rstrip": false,
26
- "single_word": false
27
- },
28
  "errors": "replace",
29
- "mask_token": {
30
- "__type": "AddedToken",
31
- "content": "<mask>",
32
- "lstrip": true,
33
- "normalized": true,
34
- "rstrip": false,
35
- "single_word": false
36
- },
37
  "max_len": 512,
38
  "model_max_length": 512,
39
- "pad_token": {
40
- "__type": "AddedToken",
41
- "content": "<pad>",
42
- "lstrip": false,
43
- "normalized": true,
44
- "rstrip": false,
45
- "single_word": false
46
- },
47
- "sep_token": {
48
- "__type": "AddedToken",
49
- "content": "</s>",
50
- "lstrip": false,
51
- "normalized": true,
52
- "rstrip": false,
53
- "single_word": false
54
- },
55
  "tokenizer_class": "RobertaTokenizer",
56
  "trim_offsets": true,
57
- "unk_token": {
58
- "__type": "AddedToken",
59
- "content": "<unk>",
60
- "lstrip": false,
61
- "normalized": true,
62
- "rstrip": false,
63
- "single_word": false
64
- }
65
  }
 
1
  {
2
  "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "[UNK]",
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": "[CLS]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "[SEP]",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "[MASK]",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "65536": {
45
+ "content": "<s>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "65537": {
53
+ "content": "</s>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "65538": {
61
+ "content": "<unk>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "65539": {
69
+ "content": "<pad>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "65540": {
77
+ "content": "<mask>",
78
+ "lstrip": true,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ }
84
  },
85
+ "additional_special_tokens": [
86
+ "[UNK]",
87
+ "[PAD]",
88
+ "[CLS]",
89
+ "[SEP]",
90
+ "[MASK]",
91
+ "<s>",
92
+ "</s>",
93
+ "<unk>",
94
+ "<pad>",
95
+ "<mask>"
96
+ ],
97
+ "bos_token": "[CLS]",
98
  "clean_up_tokenization_spaces": true,
99
+ "cls_token": "[CLS]",
100
+ "eos_token": "[SEP]",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
101
  "errors": "replace",
102
+ "mask_token": "[MASK]",
 
 
 
 
 
 
 
103
  "max_len": 512,
104
  "model_max_length": 512,
105
+ "pad_token": "[PAD]",
106
+ "sep_token": "[SEP]",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
107
  "tokenizer_class": "RobertaTokenizer",
108
  "trim_offsets": true,
109
+ "unk_token": "[UNK]"
 
 
 
 
 
 
 
110
  }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff