Hugging Face's logo

bpatel644
/
Mine

Transformers
Safetensors
CustomAI
custom_code
Inference Endpoints
Model card Files Community
bpatel644 commited on
Commit
bce2d65
•
1 Parent(s): b6ca8b9

Upload tokenizer

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +5 -28
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +35 -18
  4. vocab.txt +0 -0
special_tokens_map.json CHANGED
@@ -1,30 +1,7 @@
1
  {
2
- "bos_token": {
3
- "content": "<|startoftext|>",
4
- "lstrip": false,
5
- "normalized": true,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "<|endoftext|>",
11
- "lstrip": false,
12
- "normalized": true,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": {
17
- "content": "<unk>",
18
- "lstrip": false,
19
- "normalized": true,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "unk_token": {
24
- "content": "<unk>",
25
- "lstrip": false,
26
- "normalized": true,
27
- "rstrip": false,
28
- "single_word": false
29
- }
30
  }
 
1
  {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,38 +1,55 @@
1
  {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
  "added_tokens_decoder": {
5
  "0": {
6
- "content": "<unk>",
7
  "lstrip": false,
8
- "normalized": true,
9
  "rstrip": false,
10
  "single_word": false,
11
  "special": true
12
  },
13
- "1000": {
14
- "content": "<|startoftext|>",
15
  "lstrip": false,
16
- "normalized": true,
17
  "rstrip": false,
18
  "single_word": false,
19
  "special": true
20
  },
21
- "1001": {
22
- "content": "<|endoftext|>",
23
  "lstrip": false,
24
- "normalized": true,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
  "rstrip": false,
26
  "single_word": false,
27
  "special": true
28
  }
29
  },
30
- "bos_token": "<|startoftext|>",
31
- "clean_up_tokenization_spaces": false,
32
- "eos_token": "<|endoftext|>",
33
- "model_max_length": 1000000000000000019884624838656,
34
- "pad_token": "<unk>",
35
- "sp_model_kwargs": {},
36
- "tokenizer_class": "Tokenizer",
37
- "unk_token": "<unk>"
 
 
 
38
  }
 
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_lower_case": false,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
  }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff