Hugging Face's logo

raygx
/
Nepali_BPE_Tokenizer

Model card Files Community
raygx commited on
Commit
3b136ec
•
1 Parent(s): 8fbf4cf

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +7 -49
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +1 -50
special_tokens_map.json CHANGED
@@ -1,51 +1,9 @@
1
  {
2
- "bos_token": {
3
- "content": "[CLS]",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "cls_token": {
10
- "content": "[CLS]",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "eos_token": {
17
- "content": "[SEP]",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "mask_token": {
24
- "content": "[MASK]",
25
- "lstrip": false,
26
- "normalized": false,
27
- "rstrip": false,
28
- "single_word": false
29
- },
30
- "pad_token": {
31
- "content": "[PAD]",
32
- "lstrip": false,
33
- "normalized": false,
34
- "rstrip": false,
35
- "single_word": false
36
- },
37
- "sep_token": {
38
- "content": "[SEP]",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false
43
- },
44
- "unk_token": {
45
- "content": "[UNK]",
46
- "lstrip": false,
47
- "normalized": false,
48
- "rstrip": false,
49
- "single_word": false
50
- }
51
  }
 
1
  {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,54 +1,5 @@
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": "[CLS]",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "2": {
20
- "content": "[SEP]",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "3": {
28
- "content": "[PAD]",
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
- "bos_token": "[CLS]",
45
  "clean_up_tokenization_spaces": true,
46
- "cls_token": "[CLS]",
47
- "eos_token": "[SEP]",
48
- "mask_token": "[MASK]",
49
  "model_max_length": 1000000000000000019884624838656,
50
- "pad_token": "[PAD]",
51
- "sep_token": "[SEP]",
52
- "tokenizer_class": "PreTrainedTokenizerFast",
53
- "unk_token": "[UNK]"
54
  }
 
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "clean_up_tokenization_spaces": true,
 
 
 
3
  "model_max_length": 1000000000000000019884624838656,
4
+ "tokenizer_class": "PreTrainedTokenizerFast"
 
 
 
5
  }