Hugging Face's logo

josh-oo
/
aspect-based-embeddings-v3

Transformers
Safetensors
bert
Model card Files Community
josh-oo commited on
Commit
035c9d4
·
verified ·
1 Parent(s): 6f726e6

specter2_tokenizer

Browse files
Files changed (5) hide show
  1. added_tokens.json +6 -0
  2. special_tokens_map.json +6 -20
  3. tokenizer.json +2 -2
  4. tokenizer_config.json +55 -21
  5. vocab.txt +0 -0
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "<condition>": 31092,
3
+ "<intervention>": 31091,
4
+ "<outcome>": 31093,
5
+ "<participants>": 31090
6
+ }
special_tokens_map.json CHANGED
@@ -1,48 +1,34 @@
1
  {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
  "cls_token": {
10
- "content": "<s>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "eos_token": {
17
- "content": "</s>",
18
  "lstrip": false,
19
  "normalized": false,
20
  "rstrip": false,
21
  "single_word": false
22
  },
23
  "mask_token": {
24
- "content": "<mask>",
25
- "lstrip": true,
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": "</s>",
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,
 
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": "[MASK]",
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
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:249df0778f236f6ece390de0de746838ef25b9d6954b68c2ee71249e0a9d8fd4
3
- size 17082799
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7837c928f35ed4f272beaa0f032b6d1beb6dc585340275cba04b3c7151b038ed
3
+ size 717582
tokenizer_config.json CHANGED
@@ -1,56 +1,90 @@
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
- "content": "<s>",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
10
  },
11
- "1": {
12
- "content": "<pad>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
- "2": {
20
- "content": "</s>",
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": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
- "250001": {
36
- "content": "<mask>",
37
- "lstrip": true,
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
  }
43
  },
44
- "bos_token": "<s>",
45
- "clean_up_tokenization_spaces": true,
46
- "cls_token": "<s>",
47
- "eos_token": "</s>",
48
  "extra_special_tokens": {},
49
- "mask_token": "<mask>",
50
- "model_max_length": 512,
51
- "pad_token": "<pad>",
52
- "sep_token": "</s>",
53
- "sp_model_kwargs": {},
54
- "tokenizer_class": "XLMRobertaTokenizer",
55
- "unk_token": "<unk>"
 
 
56
  }
 
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
+ "101": {
12
+ "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
+ "102": {
20
+ "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "103": {
28
+ "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "104": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
42
+ },
43
+ "31090": {
44
+ "content": "<participants>",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "31091": {
52
+ "content": "<intervention>",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "31092": {
60
+ "content": "<condition>",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "31093": {
68
+ "content": "<outcome>",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
  }
75
  },
76
+ "clean_up_tokenization_spaces": false,
77
+ "cls_token": "[CLS]",
78
+ "do_basic_tokenize": true,
79
+ "do_lower_case": true,
80
  "extra_special_tokens": {},
81
+ "mask_token": "[MASK]",
82
+ "model_max_length": 516,
83
+ "never_split": null,
84
+ "pad_token": "[PAD]",
85
+ "sep_token": "[SEP]",
86
+ "strip_accents": null,
87
+ "tokenize_chinese_chars": true,
88
+ "tokenizer_class": "BertTokenizer",
89
+ "unk_token": "[UNK]"
90
  }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff