Hugging Face's logo

MatthijsN
/
happy

Fill-Mask
Transformers
PyTorch
roberta
Model card Files
xet
Community
2
MatthijsN commited on
Commit
8fc4d76
·
1 Parent(s): 2e8a84b

Upload tokenizer

Browse files
Files changed (5) hide show
  1. merges.txt +1 -1
  2. special_tokens_map.json +7 -43
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +8 -56
  5. vocab.json +0 -0
merges.txt CHANGED
@@ -1,4 +1,4 @@
1
- #version: 0.2
2
  Ġ t
3
  Ġ a
4
  h e
 
1
+ #version: 0.2 - Trained by `huggingface/tokenizers`
2
  Ġ t
3
  Ġ a
4
  h e
special_tokens_map.json CHANGED
@@ -1,51 +1,15 @@
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,
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
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "mask_token": {
6
  "content": "<mask>",
7
  "lstrip": true,
8
+ "normalized": false,
9
  "rstrip": false,
10
  "single_word": false
11
  },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,63 +1,15 @@
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
- "cls_token": {
12
- "__type": "AddedToken",
13
- "content": "<s>",
14
- "lstrip": false,
15
- "normalized": true,
16
- "rstrip": false,
17
- "single_word": false
18
- },
19
- "eos_token": {
20
- "__type": "AddedToken",
21
- "content": "</s>",
22
- "lstrip": false,
23
- "normalized": true,
24
- "rstrip": false,
25
- "single_word": false
26
- },
27
  "errors": "replace",
28
- "mask_token": {
29
- "__type": "AddedToken",
30
- "content": "<mask>",
31
- "lstrip": true,
32
- "normalized": true,
33
- "rstrip": false,
34
- "single_word": false
35
- },
36
  "model_max_length": 512,
37
- "pad_token": {
38
- "__type": "AddedToken",
39
- "content": "<pad>",
40
- "lstrip": false,
41
- "normalized": true,
42
- "rstrip": false,
43
- "single_word": false
44
- },
45
- "sep_token": {
46
- "__type": "AddedToken",
47
- "content": "</s>",
48
- "lstrip": false,
49
- "normalized": true,
50
- "rstrip": false,
51
- "single_word": false
52
- },
53
  "special_tokens_map_file": null,
54
  "tokenizer_class": "RobertaTokenizer",
55
- "unk_token": {
56
- "__type": "AddedToken",
57
- "content": "<unk>",
58
- "lstrip": false,
59
- "normalized": true,
60
- "rstrip": false,
61
- "single_word": false
62
- }
63
  }
 
1
  {
2
  "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  "errors": "replace",
7
+ "mask_token": "<mask>",
 
 
 
 
 
 
 
8
  "model_max_length": 512,
9
+ "pad_token": "<pad>",
10
+ "sep_token": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  "special_tokens_map_file": null,
12
  "tokenizer_class": "RobertaTokenizer",
13
+ "trim_offsets": true,
14
+ "unk_token": "<unk>"
 
 
 
 
 
 
15
  }
vocab.json CHANGED
The diff for this file is too large to render. See raw diff