Hugging Face's logo

datht
/
finance-tokenizer

Transformers
Inference Endpoints
Model card Files Community
datht commited on
Commit
06ca69e
•
1 Parent(s): 0d04258

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +7 -0
  2. special_tokens_map.json +5 -1
  3. tokenizer.json +45 -0
  4. tokenizer_config.json +45 -1
added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "[CLS]": 20114,
3
+ "[MASK]": 20116,
4
+ "[PAD]": 20113,
5
+ "[SEP]": 20115,
6
+ "[UNK]": 20112
7
+ }
special_tokens_map.json CHANGED
@@ -1,5 +1,9 @@
1
  {
2
  "bos_token": "<|endoftext|>",
 
3
  "eos_token": "<|endoftext|>",
4
- "unk_token": "<|endoftext|>"
 
 
 
5
  }
 
1
  {
2
  "bos_token": "<|endoftext|>",
3
+ "cls_token": "[CLS]",
4
  "eos_token": "<|endoftext|>",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": "[UNK]"
9
  }
tokenizer.json CHANGED
@@ -11,6 +11,51 @@
11
  "rstrip": false,
12
  "normalized": true,
13
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  }
15
  ],
16
  "normalizer": null,
 
11
  "rstrip": false,
12
  "normalized": true,
13
  "special": true
14
+ },
15
+ {
16
+ "id": 20112,
17
+ "content": "[UNK]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 20113,
26
+ "content": "[PAD]",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 20114,
35
+ "content": "[CLS]",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 20115,
44
+ "content": "[SEP]",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 20116,
53
+ "content": "[MASK]",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
  }
60
  ],
61
  "normalizer": null,
tokenizer_config.json CHANGED
@@ -8,12 +8,56 @@
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  }
12
  },
13
  "bos_token": "<|endoftext|>",
14
  "clean_up_tokenization_spaces": true,
 
15
  "eos_token": "<|endoftext|>",
 
16
  "model_max_length": 1024,
 
 
17
  "tokenizer_class": "GPT2Tokenizer",
18
- "unk_token": "<|endoftext|>"
19
  }
 
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
+ },
12
+ "20112": {
13
+ "content": "[UNK]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "20113": {
21
+ "content": "[PAD]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "20114": {
29
+ "content": "[CLS]",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "20115": {
37
+ "content": "[SEP]",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "20116": {
45
+ "content": "[MASK]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
  }
52
  },
53
  "bos_token": "<|endoftext|>",
54
  "clean_up_tokenization_spaces": true,
55
+ "cls_token": "[CLS]",
56
  "eos_token": "<|endoftext|>",
57
+ "mask_token": "[MASK]",
58
  "model_max_length": 1024,
59
+ "pad_token": "[PAD]",
60
+ "sep_token": "[SEP]",
61
  "tokenizer_class": "GPT2Tokenizer",
62
+ "unk_token": "[UNK]"
63
  }