Hugging Face's logo

josem7
/
SQL-SURI-13B-v0.2

Text Generation
Transformers
PyTorch
llama
text-generation-inference
Model card Files
xet
Community
1
josem7 commited on
Commit
3d3831d
·
1 Parent(s): c689747

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +28 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +109 -0
special_tokens_map.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "▁<PRE>",
4
+ "▁<SUF>",
5
+ "▁<MID>",
6
+ "▁<EOT>",
7
+ "▁<PRE>",
8
+ "▁<MID>",
9
+ "▁<SUF>",
10
+ "▁<EOT>",
11
+ "<unk>",
12
+ "<s>",
13
+ "</s>",
14
+ "▁<PRE>",
15
+ "▁<SUF>",
16
+ "▁<MID>",
17
+ "▁<EOT>",
18
+ "<PAD>",
19
+ "▁<PRE>",
20
+ "▁<MID>",
21
+ "▁<SUF>",
22
+ "▁<EOT>"
23
+ ],
24
+ "bos_token": "<s>",
25
+ "eos_token": "</s>",
26
+ "pad_token": "<PAD>",
27
+ "unk_token": "<unk>"
28
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
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
+ "32007": {
28
+ "content": "▁<PRE>",
29
+ "lstrip": true,
30
+ "normalized": false,
31
+ "rstrip": true,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "32008": {
36
+ "content": "▁<SUF>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": true,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "32009": {
44
+ "content": "▁<MID>",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": true,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "32010": {
52
+ "content": "▁<EOT>",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": true,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "32016": {
60
+ "content": "<PAD>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ }
67
+ },
68
+ "additional_special_tokens": [
69
+ "▁<PRE>",
70
+ "▁<SUF>",
71
+ "▁<MID>",
72
+ "▁<EOT>",
73
+ "▁<PRE>",
74
+ "▁<MID>",
75
+ "▁<SUF>",
76
+ "▁<EOT>",
77
+ "<unk>",
78
+ "<s>",
79
+ "</s>",
80
+ "▁<PRE>",
81
+ "▁<SUF>",
82
+ "▁<MID>",
83
+ "▁<EOT>",
84
+ "<PAD>",
85
+ "▁<PRE>",
86
+ "▁<MID>",
87
+ "▁<SUF>",
88
+ "▁<EOT>"
89
+ ],
90
+ "bos_token": "<s>",
91
+ "clean_up_tokenization_spaces": false,
92
+ "eos_token": "</s>",
93
+ "eot_token": "▁<EOT>",
94
+ "fill_token": "<FILL_ME>",
95
+ "legacy": null,
96
+ "max_length": 4096,
97
+ "middle_token": "▁<MID>",
98
+ "model_max_length": 1000000000000000019884624838656,
99
+ "pad_token": "<PAD>",
100
+ "prefix_token": "▁<PRE>",
101
+ "sp_model_kwargs": {},
102
+ "stride": 0,
103
+ "suffix_token": "▁<SUF>",
104
+ "tokenizer_class": "CodeLlamaTokenizer",
105
+ "truncation_side": "right",
106
+ "truncation_strategy": "longest_first",
107
+ "unk_token": "<unk>",
108
+ "use_default_system_prompt": false
109
+ }