Hugging Face's logo

chi-vi
/
chivi-lert-base

Fill-Mask
Transformers
Safetensors
Chinese
bert
Model card Files
xet
 Community
b3x0m commited on
Commit
e91f458
·
verified ·
1 Parent(s): 477d8ef

Upload tokenizer

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +9 -9
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +24 -22
  4. vocab.txt +0 -0
special_tokens_map.json CHANGED
@@ -1,34 +1,34 @@
1
  {
2
- "bos_token": {
3
- "content": "<s>",
4
  "lstrip": false,
5
  "normalized": false,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
- "eos_token": {
10
- "content": "</s>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
- "mask_token": {
17
- "content": "<unk>",
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
  "unk_token": {
31
- "content": "<unk>",
32
  "lstrip": false,
33
  "normalized": false,
34
  "rstrip": false,
 
1
  {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
  "lstrip": false,
5
  "normalized": false,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
+ "mask_token": {
10
+ "content": "[UNK]",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
  "lstrip": false,
19
  "normalized": false,
20
  "rstrip": false,
21
  "single_word": false
22
  },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
  "lstrip": false,
26
  "normalized": false,
27
  "rstrip": false,
28
  "single_word": false
29
  },
30
  "unk_token": {
31
+ "content": "[UNK]",
32
  "lstrip": false,
33
  "normalized": false,
34
  "rstrip": false,
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,34 +1,39 @@
1
  {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
- "add_prefix_space": null,
5
  "added_tokens_decoder": {
6
  "0": {
7
- "content": "<unk>",
8
  "lstrip": false,
9
  "normalized": false,
10
  "rstrip": false,
11
  "single_word": false,
12
  "special": true
13
  },
14
- "1": {
15
- "content": "<s>",
16
  "lstrip": false,
17
  "normalized": false,
18
  "rstrip": false,
19
  "single_word": false,
20
  "special": true
21
  },
22
- "2": {
23
- "content": "</s>",
24
  "lstrip": false,
25
  "normalized": false,
26
  "rstrip": false,
27
  "single_word": false,
28
  "special": true
29
  },
30
- "25000": {
31
- "content": "<pad>",
 
 
 
 
 
 
 
 
32
  "lstrip": false,
33
  "normalized": false,
34
  "rstrip": false,
@@ -36,19 +41,16 @@
36
  "special": true
37
  }
38
  },
39
- "bos_token": "<s>",
40
- "bos_token_id": 1,
41
  "clean_up_tokenization_spaces": false,
42
- "eos_token": "</s>",
43
- "eos_token_id": 2,
44
  "extra_special_tokens": {},
45
- "legacy": true,
46
- "mask_token": "<unk>",
47
- "max_model_input_sizes": 2048,
48
  "model_max_length": 1000000000000000019884624838656,
49
- "pad_token": "<pad>",
50
- "tokenizer_class": "PreTrainedTokenizer",
51
- "unk_token": "<unk>",
52
- "unk_token_id": 0,
53
- "use_default_system_prompt": false
 
54
  }
 
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,
 
41
  "special": true
42
  }
43
  },
 
 
44
  "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
  "extra_special_tokens": {},
48
+ "mask_token": "[UNK]",
 
 
49
  "model_max_length": 1000000000000000019884624838656,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
  }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff