MoritzLaurer HF staff commited on
Commit
b44d453
1 Parent(s): a5f643b

Upload tokenizer

Browse files
Files changed (5) hide show
  1. README.md +1 -1
  2. special_tokens_map.json +6 -42
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +1 -0
  5. vocab.json +0 -0
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
  license: mit
3
- base_model: FacebookAI/roberta-large
4
  tags:
5
  - generated_from_trainer
 
6
  metrics:
7
  - accuracy
8
  model-index:
 
1
  ---
2
  license: mit
 
3
  tags:
4
  - generated_from_trainer
5
+ base_model: FacebookAI/roberta-large
6
  metrics:
7
  - accuracy
8
  model-index:
special_tokens_map.json CHANGED
@@ -1,25 +1,7 @@
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,
@@ -27,25 +9,7 @@
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,
 
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
@@ -52,5 +52,6 @@
52
  "pad_token": "<pad>",
53
  "sep_token": "</s>",
54
  "tokenizer_class": "RobertaTokenizer",
 
55
  "unk_token": "<unk>"
56
  }
 
52
  "pad_token": "<pad>",
53
  "sep_token": "</s>",
54
  "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
  "unk_token": "<unk>"
57
  }
vocab.json CHANGED
The diff for this file is too large to render. See raw diff