Hugging Face's logo

avey-ai
/
avey-b1-base-exp

Fill-Mask
Transformers
Safetensors
English
avey-b
custom_code
Model card Files
xet
 Community
rainnekoneko commited on
Commit
3cebfc0
·
1 Parent(s): 4125545

update tokenizer with bert special tokens

Browse files
Files changed (4) hide show
  1. added_tokens.json +5 -1
  2. special_tokens_map.json +22 -1
  3. tokenizer.json +36 -0
  4. tokenizer_config.json +36 -1
added_tokens.json CHANGED
@@ -1,4 +1,8 @@
1
  {
2
  "<|endoftext|>": 50280,
3
- "[MASK]": 50281
 
 
 
 
4
  }
 
1
  {
2
  "<|endoftext|>": 50280,
3
+ "[CLS]": 50284,
4
+ "[MASK]": 50281,
5
+ "[PAD]": 50283,
6
+ "[SEP]": 50285,
7
+ "[UNK]": 50282
8
  }
special_tokens_map.json CHANGED
@@ -6,6 +6,13 @@
6
  "rstrip": false,
7
  "single_word": false
8
  },
 
 
 
 
 
 
 
9
  "eos_token": {
10
  "content": "<|endoftext|>",
11
  "lstrip": false,
@@ -20,8 +27,22 @@
20
  "rstrip": false,
21
  "single_word": false
22
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
23
  "unk_token": {
24
- "content": "<|endoftext|>",
25
  "lstrip": false,
26
  "normalized": false,
27
  "rstrip": false,
 
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
  "eos_token": {
17
  "content": "<|endoftext|>",
18
  "lstrip": 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": "[SEP]",
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,
tokenizer.json CHANGED
@@ -20,6 +20,42 @@
20
  "rstrip": false,
21
  "normalized": false,
22
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
23
  }
24
  ],
25
  "normalizer": null,
 
20
  "rstrip": false,
21
  "normalized": false,
22
  "special": true
23
+ },
24
+ {
25
+ "id": 50282,
26
+ "content": "[UNK]",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 50283,
35
+ "content": "[PAD]",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 50284,
44
+ "content": "[CLS]",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 50285,
53
+ "content": "[SEP]",
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
@@ -16,14 +16,49 @@
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
19
  }
20
  },
21
  "bos_token": "<|endoftext|>",
22
  "clean_up_tokenization_spaces": false,
 
23
  "eos_token": "<|endoftext|>",
24
  "extra_special_tokens": {},
25
  "mask_token": "[MASK]",
26
  "model_max_length": 4294967296,
 
 
27
  "tokenizer_class": "GPT2Tokenizer",
28
- "unk_token": "<|endoftext|>"
29
  }
 
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
19
+ },
20
+ "50282": {
21
+ "content": "[UNK]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "50283": {
29
+ "content": "[PAD]",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50284": {
37
+ "content": "[CLS]",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "50285": {
45
+ "content": "[SEP]",
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": false,
55
+ "cls_token": "[CLS]",
56
  "eos_token": "<|endoftext|>",
57
  "extra_special_tokens": {},
58
  "mask_token": "[MASK]",
59
  "model_max_length": 4294967296,
60
+ "pad_token": "[PAD]",
61
+ "sep_token": "[SEP]",
62
  "tokenizer_class": "GPT2Tokenizer",
63
+ "unk_token": "[UNK]"
64
  }