Hugging Face's logo

scthornton
/
codellama-13b-securecode

Text Generation
PEFT
TensorBoard
Safetensors
code
English
security
cybersecurity
secure-coding
ai-security
owasp
code-generation
lora
fine-tuned
securecode
conversational
Model card Files
xet
 Metrics Community
2
scthornton commited on
Commit
5db4b2d
·
verified ·
1 Parent(s): 98cc646

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +11 -1
  2. tokenizer.json +38 -16
  3. tokenizer_config.json +83 -4
special_tokens_map.json CHANGED
@@ -1,5 +1,9 @@
1
  {
2
  "additional_special_tokens": [
 
 
 
 
3
  "▁<PRE>",
4
  "▁<MID>",
5
  "▁<SUF>",
@@ -19,7 +23,13 @@
19
  "rstrip": false,
20
  "single_word": false
21
  },
22
- "pad_token": "</s>",
 
 
 
 
 
 
23
  "unk_token": {
24
  "content": "<unk>",
25
  "lstrip": false,
 
1
  {
2
  "additional_special_tokens": [
3
+ "▁<PRE>",
4
+ "▁<MID>",
5
+ "▁<SUF>",
6
+ "▁<EOT>",
7
  "▁<PRE>",
8
  "▁<MID>",
9
  "▁<SUF>",
 
23
  "rstrip": false,
24
  "single_word": false
25
  },
26
+ "pad_token": {
27
+ "content": "</s>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
  "unk_token": {
34
  "content": "<unk>",
35
  "lstrip": false,
tokenizer.json CHANGED
@@ -1,21 +1,7 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 2048,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
- "padding": {
10
- "strategy": {
11
- "Fixed": 2048
12
- },
13
- "direction": "Right",
14
- "pad_to_multiple_of": null,
15
- "pad_id": 2,
16
- "pad_type_id": 0,
17
- "pad_token": "</s>"
18
- },
19
  "added_tokens": [
20
  {
21
  "id": 0,
@@ -43,6 +29,42 @@
43
  "rstrip": false,
44
  "normalized": false,
45
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
46
  }
47
  ],
48
  "normalizer": {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 0,
 
29
  "rstrip": false,
30
  "normalized": false,
31
  "special": true
32
+ },
33
+ {
34
+ "id": 32007,
35
+ "content": "▁<PRE>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 32008,
44
+ "content": "▁<SUF>",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 32009,
53
+ "content": "▁<MID>",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
+ },
60
+ {
61
+ "id": 32010,
62
+ "content": "▁<EOT>",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": false,
67
+ "special": true
68
  }
69
  ],
70
  "normalizer": {
tokenizer_config.json CHANGED
@@ -1,13 +1,92 @@
1
  {
2
- "backend": "tokenizers",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "bos_token": "<s>",
4
  "clean_up_tokenization_spaces": false,
5
  "eos_token": "</s>",
6
- "is_local": false,
 
 
7
  "legacy": null,
 
 
8
  "model_max_length": 1000000000000000019884624838656,
9
  "pad_token": "</s>",
 
10
  "sp_model_kwargs": {},
11
- "tokenizer_class": "TokenizersBackend",
12
- "unk_token": "<unk>"
 
 
 
 
 
13
  }
 
1
  {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
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
+ "▁<PRE>",
68
+ "▁<MID>",
69
+ "▁<SUF>",
70
+ "▁<EOT>"
71
+ ],
72
  "bos_token": "<s>",
73
  "clean_up_tokenization_spaces": false,
74
  "eos_token": "</s>",
75
+ "eot_token": "▁<EOT>",
76
+ "extra_special_tokens": {},
77
+ "fill_token": "<FILL_ME>",
78
  "legacy": null,
79
+ "max_length": 2048,
80
+ "middle_token": "▁<MID>",
81
  "model_max_length": 1000000000000000019884624838656,
82
  "pad_token": "</s>",
83
+ "prefix_token": "▁<PRE>",
84
  "sp_model_kwargs": {},
85
+ "stride": 0,
86
+ "suffix_token": "▁<SUF>",
87
+ "tokenizer_class": "CodeLlamaTokenizer",
88
+ "truncation_side": "right",
89
+ "truncation_strategy": "longest_first",
90
+ "unk_token": "<unk>",
91
+ "use_default_system_prompt": false
92
  }