DJDeep commited on
Commit
4512909
·
verified ·
1 Parent(s): 3e30797

Upload folder using huggingface_hub

Browse files
special_tokens_map.json CHANGED
@@ -1,7 +1,37 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
 
1
  {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
  }
tokenizer.json CHANGED
@@ -1,14 +1,7 @@
1
  {
2
  "version": "1.0",
3
  "truncation": null,
4
- "padding": {
5
- "strategy": "BatchLongest",
6
- "direction": "Right",
7
- "pad_to_multiple_of": null,
8
- "pad_id": 0,
9
- "pad_type_id": 0,
10
- "pad_token": "[PAD]"
11
- },
12
  "added_tokens": [
13
  {
14
  "id": 0,
 
1
  {
2
  "version": "1.0",
3
  "truncation": null,
4
+ "padding": null,
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 0,
tokenizer_config.json CHANGED
@@ -47,9 +47,13 @@
47
  "do_lower_case": true,
48
  "extra_special_tokens": {},
49
  "mask_token": "[MASK]",
 
50
  "model_max_length": 1000000000000000019884624838656,
51
  "never_split": null,
 
52
  "pad_token": "[PAD]",
 
 
53
  "sep_token": "[SEP]",
54
  "strip_accents": null,
55
  "tokenize_chinese_chars": true,
 
47
  "do_lower_case": true,
48
  "extra_special_tokens": {},
49
  "mask_token": "[MASK]",
50
+ "max_length": null,
51
  "model_max_length": 1000000000000000019884624838656,
52
  "never_split": null,
53
+ "pad_to_multiple_of": null,
54
  "pad_token": "[PAD]",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
  "sep_token": "[SEP]",
58
  "strip_accents": null,
59
  "tokenize_chinese_chars": true,