Hugging Face's logo

nono1224
/
b3comp-luke-1

Text Classification
Transformers
Safetensors
modernbert
text-embeddings-inference
Model card Files
xet
 Community
nono1224 commited on
Commit
3f62c75
·
verified ·
1 Parent(s): 52aef45

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +2 -1
  2. special_tokens_map.json +73 -7
  3. tokenizer_config.json +52 -23
added_tokens.json CHANGED
@@ -1,3 +1,4 @@
1
  {
2
- "[MASK]": 128000
 
3
  }
 
1
  {
2
+ "<ent2>": 50266,
3
+ "<ent>": 50265
4
  }
special_tokens_map.json CHANGED
@@ -1,12 +1,78 @@
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": {
9
- "content": "[UNK]",
10
  "lstrip": false,
11
  "normalized": true,
12
  "rstrip": false,
 
1
  {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<ent>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<ent2>",
12
+ "lstrip": false,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<ent>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "<ent2>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ ],
32
+ "bos_token": {
33
+ "content": "<s>",
34
+ "lstrip": false,
35
+ "normalized": true,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ },
39
+ "cls_token": {
40
+ "content": "<s>",
41
+ "lstrip": false,
42
+ "normalized": true,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "eos_token": {
47
+ "content": "</s>",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ },
53
+ "mask_token": {
54
+ "content": "<mask>",
55
+ "lstrip": true,
56
+ "normalized": true,
57
+ "rstrip": false,
58
+ "single_word": false
59
+ },
60
+ "pad_token": {
61
+ "content": "<pad>",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false
66
+ },
67
+ "sep_token": {
68
+ "content": "</s>",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false
73
+ },
74
  "unk_token": {
75
+ "content": "<unk>",
76
  "lstrip": false,
77
  "normalized": true,
78
  "rstrip": false,
tokenizer_config.json CHANGED
@@ -1,59 +1,88 @@
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
  "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": "[UNK]",
29
  "lstrip": false,
30
  "normalized": true,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
- "128000": {
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": false,
46
- "cls_token": "[CLS]",
47
- "do_lower_case": false,
48
- "eos_token": "[SEP]",
 
 
 
 
 
 
49
  "extra_special_tokens": {},
50
- "mask_token": "[MASK]",
51
- "model_max_length": 1000000000000000019884624838656,
52
- "pad_token": "[PAD]",
53
- "sep_token": "[SEP]",
54
- "sp_model_kwargs": {},
55
- "split_by_punct": false,
56
- "tokenizer_class": "DebertaV2Tokenizer",
57
- "unk_token": "[UNK]",
58
- "vocab_type": "spm"
59
  }
 
1
  {
2
+ "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
  "0": {
5
+ "content": "<s>",
6
  "lstrip": false,
7
+ "normalized": true,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  },
12
  "1": {
13
+ "content": "<pad>",
14
  "lstrip": false,
15
+ "normalized": true,
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
19
  },
20
  "2": {
21
+ "content": "</s>",
22
  "lstrip": false,
23
+ "normalized": true,
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
27
  },
28
  "3": {
29
+ "content": "<unk>",
30
  "lstrip": false,
31
  "normalized": true,
32
  "rstrip": false,
33
  "single_word": false,
34
  "special": true
35
  },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "50265": {
45
+ "content": "<ent>",
46
  "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "50266": {
53
+ "content": "<ent2>",
54
+ "lstrip": false,
55
+ "normalized": true,
56
  "rstrip": false,
57
  "single_word": false,
58
  "special": true
59
  }
60
  },
61
+ "additional_special_tokens": [
62
+ "<ent>",
63
+ "<ent2>",
64
+ "<ent>",
65
+ "<ent2>"
66
+ ],
67
+ "bos_token": "<s>",
68
  "clean_up_tokenization_spaces": false,
69
+ "cls_token": "<s>",
70
+ "entity_mask2_token": "[MASK2]",
71
+ "entity_mask_token": "[MASK]",
72
+ "entity_pad_token": "[PAD]",
73
+ "entity_token_1": "<ent>",
74
+ "entity_token_2": "<ent2>",
75
+ "entity_unk_token": "[UNK]",
76
+ "eos_token": "</s>",
77
+ "errors": "replace",
78
  "extra_special_tokens": {},
79
+ "mask_token": "<mask>",
80
+ "max_entity_length": 32,
81
+ "max_mention_length": 30,
82
+ "model_max_length": 512,
83
+ "pad_token": "<pad>",
84
+ "sep_token": "</s>",
85
+ "task": null,
86
+ "tokenizer_class": "LukeTokenizer",
87
+ "unk_token": "<unk>"
88
  }