ani-kavle commited on
Commit
1711293
β€’
1 Parent(s): 52ccdb4

Upload tokenizer

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +6 -1
  2. tokenizer_config.json +47 -7
special_tokens_map.json CHANGED
@@ -1,4 +1,10 @@
1
  {
 
 
 
 
 
 
2
  "bos_token": {
3
  "content": "<s>",
4
  "lstrip": false,
@@ -13,7 +19,6 @@
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
- "pad_token": "</s>",
17
  "unk_token": {
18
  "content": "<unk>",
19
  "lstrip": false,
 
1
  {
2
+ "additional_special_tokens": [
3
+ "▁<PRE>",
4
+ "▁<MID>",
5
+ "▁<SUF>",
6
+ "▁<EOT>"
7
+ ],
8
  "bos_token": {
9
  "content": "<s>",
10
  "lstrip": false,
 
19
  "rstrip": false,
20
  "single_word": false
21
  },
 
22
  "unk_token": {
23
  "content": "<unk>",
24
  "lstrip": false,
tokenizer_config.json CHANGED
@@ -1,7 +1,6 @@
1
  {
2
  "add_bos_token": true,
3
  "add_eos_token": false,
4
- "add_prefix_space": true,
5
  "added_tokens_decoder": {
6
  "0": {
7
  "content": "<unk>",
@@ -26,18 +25,59 @@
26
  "rstrip": false,
27
  "single_word": false,
28
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
29
  }
30
  },
 
 
 
 
 
 
31
  "bos_token": "<s>",
32
  "clean_up_tokenization_spaces": false,
33
  "eos_token": "</s>",
34
- "legacy": true,
 
 
 
35
  "model_max_length": 1000000000000000019884624838656,
36
- "pad_token": "</s>",
 
37
  "sp_model_kwargs": {},
38
- "spaces_between_special_tokens": false,
39
- "tokenizer_class": "LlamaTokenizer",
40
  "unk_token": "<unk>",
41
- "use_default_system_prompt": false,
42
- "use_fast": true
43
  }
 
1
  {
2
  "add_bos_token": true,
3
  "add_eos_token": false,
 
4
  "added_tokens_decoder": {
5
  "0": {
6
  "content": "<unk>",
 
25
  "rstrip": false,
26
  "single_word": false,
27
  "special": true
28
+ },
29
+ "32007": {
30
+ "content": "▁<PRE>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32008": {
38
+ "content": "▁<SUF>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32009": {
46
+ "content": "▁<MID>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "32010": {
54
+ "content": "▁<EOT>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
  }
61
  },
62
+ "additional_special_tokens": [
63
+ "▁<PRE>",
64
+ "▁<MID>",
65
+ "▁<SUF>",
66
+ "▁<EOT>"
67
+ ],
68
  "bos_token": "<s>",
69
  "clean_up_tokenization_spaces": false,
70
  "eos_token": "</s>",
71
+ "eot_token": "▁<EOT>",
72
+ "fill_token": "<FILL_ME>",
73
+ "legacy": null,
74
+ "middle_token": "▁<MID>",
75
  "model_max_length": 1000000000000000019884624838656,
76
+ "pad_token": null,
77
+ "prefix_token": "▁<PRE>",
78
  "sp_model_kwargs": {},
79
+ "suffix_token": "▁<SUF>",
80
+ "tokenizer_class": "CodeLlamaTokenizer",
81
  "unk_token": "<unk>",
82
+ "use_default_system_prompt": false
 
83
  }