Hugging Face's logo

djohari
/
EmployeeEmotionAnalysis

Text Classification
Transformers
Safetensors
distilbert
Model card Files
xet
Community
djohari commited on
Commit
66e2c73
·
verified ·
1 Parent(s): a8795c5

Upload tokenizer

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +5 -19
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +21 -54
  4. vocab.txt +0 -0
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": false,
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
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,90 +1,57 @@
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
- "4": {
36
- "content": "<mask>",
37
  "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
42
- },
43
- "430": {
44
- "content": "@usuario",
45
- "lstrip": false,
46
- "normalized": true,
47
- "rstrip": false,
48
- "single_word": false,
49
- "special": false
50
- },
51
- "27394": {
52
- "content": "url",
53
- "lstrip": false,
54
- "normalized": true,
55
- "rstrip": false,
56
- "single_word": false,
57
- "special": false
58
- },
59
- "30000": {
60
- "content": "hashtag",
61
- "lstrip": false,
62
- "normalized": true,
63
- "rstrip": false,
64
- "single_word": false,
65
- "special": false
66
- },
67
- "30001": {
68
- "content": "emoji",
69
- "lstrip": false,
70
- "normalized": true,
71
- "rstrip": false,
72
- "single_word": false,
73
- "special": false
74
  }
75
  },
76
- "bos_token": "<s>",
77
  "clean_up_tokenization_spaces": true,
78
- "cls_token": "<s>",
79
- "eos_token": "</s>",
80
- "mask_token": "<mask>",
81
- "max_length": 128,
82
- "model_max_length": 128,
83
- "pad_token": "<pad>",
84
- "sep_token": "</s>",
85
- "stride": 0,
86
- "tokenizer_class": "PreTrainedTokenizerFast",
87
- "truncation_side": "right",
88
- "truncation_strategy": "longest_first",
89
- "unk_token": "<unk>"
90
  }
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "DistilBertTokenizer",
56
+ "unk_token": "[UNK]"
57
  }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff