Hugging Face's logo

dakadkart
/
Firstmodel

Text Generation
Transformers
PyTorch
gpt2
text-generation-inference
Model card Files
xet
Community
1
dakadkart commited on
Commit
740aa4c
·
1 Parent(s): e977cf2

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +1 -5
  2. special_tokens_map.json +4 -10
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +12 -51
added_tokens.json CHANGED
@@ -1,7 +1,3 @@
1
  {
2
- "[CLS]": 101,
3
- "[MASK]": 103,
4
- "[PAD]": 0,
5
- "[SEP]": 102,
6
- "[UNK]": 100
7
  }
 
1
  {
2
+ "<|endoftext|>": 50256
 
 
 
 
3
  }
special_tokens_map.json CHANGED
@@ -1,14 +1,8 @@
1
  {
2
  "additional_special_tokens": [
3
- "[PAD]",
4
- "[UNK]",
5
- "[CLS]",
6
- "[SEP]",
7
- "[MASK]"
8
  ],
9
- "cls_token": "[CLS]",
10
- "mask_token": "[MASK]",
11
- "pad_token": "[PAD]",
12
- "sep_token": "[SEP]",
13
- "unk_token": "[UNK]"
14
  }
 
1
  {
2
  "additional_special_tokens": [
3
+ "<|endoftext|>"
 
 
 
 
4
  ],
5
+ "bos_token": "<|endoftext|>",
6
+ "eos_token": "<|endoftext|>",
7
+ "unk_token": "<|endoftext|>"
 
 
8
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,39 +1,9 @@
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,
@@ -42,23 +12,14 @@
42
  }
43
  },
44
  "additional_special_tokens": [
45
- "[PAD]",
46
- "[UNK]",
47
- "[CLS]",
48
- "[SEP]",
49
- "[MASK]"
50
  ],
 
51
  "clean_up_tokenization_spaces": true,
52
- "cls_token": "[CLS]",
53
- "do_basic_tokenize": true,
54
- "do_lower_case": true,
55
- "mask_token": "[MASK]",
56
- "model_max_length": 512,
57
- "never_split": null,
58
- "pad_token": "[PAD]",
59
- "sep_token": "[SEP]",
60
- "strip_accents": null,
61
- "tokenize_chinese_chars": true,
62
- "tokenizer_class": "BertTokenizer",
63
- "unk_token": "[UNK]"
64
  }
 
1
  {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
  "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  "lstrip": false,
8
  "normalized": false,
9
  "rstrip": false,
 
12
  }
13
  },
14
  "additional_special_tokens": [
15
+ "<|endoftext|>"
 
 
 
 
16
  ],
17
+ "bos_token": "<|endoftext|>",
18
  "clean_up_tokenization_spaces": true,
19
+ "eos_token": "<|endoftext|>",
20
+ "errors": "replace",
21
+ "model_max_length": 1024,
22
+ "pad_token": null,
23
+ "tokenizer_class": "GPT2Tokenizer",
24
+ "unk_token": "<|endoftext|>"
 
 
 
 
 
 
25
  }