Hugging Face's logo

raygx
/
Nepali_BPE_Tokenizer

Model card Files Community
raygx commited on
Commit
bf56c21
•
1 Parent(s): 58d2b62

V3: Trained On Tpu

Browse files
Files changed (4) hide show
  1. README.md +3 -0
  2. special_tokens_map.json +28 -5
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +54 -0
README.md CHANGED
@@ -1,3 +1,6 @@
 
 
 
1
  # This is only a tokenizer.
2
 
3
  - This tokenizer is a PreTrainedTokenizerFast which is trained on raygx/Nepali-Extended-Corpus datasets.
 
1
+ ---
2
+ {}
3
+ ---
4
  # This is only a tokenizer.
5
 
6
  - This tokenizer is a PreTrainedTokenizerFast which is trained on raygx/Nepali-Extended-Corpus datasets.
special_tokens_map.json CHANGED
@@ -1,7 +1,30 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "[SEP]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "mask_token": {
17
+ "content": "MASK",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "pad_token": {
24
+ "content": "[PAD]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,5 +1,59 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "clean_up_tokenization_spaces": true,
 
 
3
  "model_max_length": 1000000000000000019884624838656,
 
4
  "tokenizer_class": "PreTrainedTokenizerFast"
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
+ "50000": {
44
+ "content": "MASK",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ }
51
+ },
52
+ "bos_token": "[CLS]",
53
  "clean_up_tokenization_spaces": true,
54
+ "eos_token": "[SEP]",
55
+ "mask_token": "MASK",
56
  "model_max_length": 1000000000000000019884624838656,
57
+ "pad_token": "[PAD]",
58
  "tokenizer_class": "PreTrainedTokenizerFast"
59
  }