mandelakori commited on
Commit
92b4e56
1 Parent(s): a6e7a2b

Update tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +7 -48
tokenizer_config.json CHANGED
@@ -1,62 +1,21 @@
1
  {
2
- "added_tokens_decoder": {
3
- "0": {
4
- "content": "[PAD]",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "100": {
12
- "content": "[UNK]",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "101": {
20
- "content": "[CLS]",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "102": {
28
- "content": "[SEP]",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "103": {
36
- "content": "[MASK]",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- }
43
- },
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_input_names": [
50
- "input_ids",
51
- "attention_mask"
52
- ],
53
  "model_max_length": 512,
 
54
  "never_split": null,
55
  "pad_token": "[PAD]",
56
  "processor_class": "BlipProcessor",
57
  "sep_token": "[SEP]",
 
58
  "strip_accents": null,
59
  "tokenize_chinese_chars": true,
60
  "tokenizer_class": "BertTokenizer",
61
- "unk_token": "[UNK]"
 
 
 
 
62
  }
 
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "cls_token": "[CLS]",
3
  "do_basic_tokenize": true,
4
  "do_lower_case": true,
5
  "mask_token": "[MASK]",
 
 
 
 
6
  "model_max_length": 512,
7
+ "name_or_path": "mandelakori/aisak-listen-beta",
8
  "never_split": null,
9
  "pad_token": "[PAD]",
10
  "processor_class": "BlipProcessor",
11
  "sep_token": "[SEP]",
12
+ "special_tokens_map_file": null,
13
  "strip_accents": null,
14
  "tokenize_chinese_chars": true,
15
  "tokenizer_class": "BertTokenizer",
16
+ "unk_token": "[UNK]",
17
+ "model_input_names": [
18
+ "input_ids",
19
+ "attention_mask"
20
+ ]
21
  }