tahaenesaslanturk commited on
Commit
ea1f0cd
1 Parent(s): 690205f

Delete ts-corpus-wordpiece-32k-uncased

Browse files
ts-corpus-wordpiece-32k-uncased/special_tokens_map.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
7
- }
 
 
 
 
 
 
 
 
ts-corpus-wordpiece-32k-uncased/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
ts-corpus-wordpiece-32k-uncased/tokenizer_config.json DELETED
@@ -1,52 +0,0 @@
1
- {
2
- "added_tokens_decoder": {
3
- "0": {
4
- "content": "[UNK]",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "1": {
12
- "content": "[PAD]",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "2": {
20
- "content": "[CLS]",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "3": {
28
- "content": "[SEP]",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "4": {
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
- "mask_token": "[MASK]",
47
- "model_max_length": 1000000000000000019884624838656,
48
- "pad_token": "[PAD]",
49
- "sep_token": "[SEP]",
50
- "tokenizer_class": "PreTrainedTokenizerFast",
51
- "unk_token": "[UNK]"
52
- }