Nico97 commited on
Commit
0fb2e74
1 Parent(s): 1d1e0c4

Upload tokenizer

Browse files
Files changed (3) hide show
  1. README.md +1 -1
  2. tokenizer_config.json +5 -5
  3. vocab.txt +0 -0
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
- license: apache-2.0
3
  base_model: bert-base-uncased
 
4
  tags:
5
  - generated_from_keras_callback
6
  model-index:
 
1
  ---
 
2
  base_model: bert-base-uncased
3
+ license: apache-2.0
4
  tags:
5
  - generated_from_keras_callback
6
  model-index:
tokenizer_config.json CHANGED
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": true
10
  },
11
- "2": {
12
  "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": true
18
  },
19
- "3": {
20
  "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "4": {
28
  "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
@@ -32,7 +32,7 @@
32
  "single_word": false,
33
  "special": true
34
  },
35
- "5": {
36
  "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
@@ -44,7 +44,7 @@
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
  "do_basic_tokenize": true,
47
- "do_lower_case": false,
48
  "mask_token": "[MASK]",
49
  "model_max_length": 512,
50
  "never_split": null,
 
8
  "single_word": false,
9
  "special": true
10
  },
11
+ "100": {
12
  "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": true
18
  },
19
+ "101": {
20
  "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "102": {
28
  "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
 
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "103": {
36
  "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
 
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
  "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
  "mask_token": "[MASK]",
49
  "model_max_length": 512,
50
  "never_split": null,
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff