Hugging Face's logo

GoCodeo
/
TestCodeo

Text Generation
Transformers
PyTorch
llama
text-generation-inference
Inference Endpoints
Model card Files Community
jatingocodeo commited on
Commit
1503fba
•
1 Parent(s): 8a13e94

Upload tokenizer

Browse files
Files changed (5) hide show
  1. added_tokens.json +6 -0
  2. special_tokens_map.json +52 -0
  3. tokenizer.json +0 -0
  4. tokenizer.model +3 -0
  5. tokenizer_config.json +97 -0
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "▁<EOT>": 32003,
3
+ "▁<MID>": 32001,
4
+ "▁<PRE>": 32000,
5
+ "▁<SUF>": 32002
6
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "▁<PRE>",
4
+ "▁<MID>",
5
+ "▁<SUF>",
6
+ "▁<EOT>",
7
+ "▁<PRE>",
8
+ "▁<MID>",
9
+ "▁<SUF>",
10
+ "▁<EOT>",
11
+ "▁<PRE>",
12
+ "▁<MID>",
13
+ "▁<SUF>",
14
+ "▁<EOT>",
15
+ "▁<PRE>",
16
+ "▁<MID>",
17
+ "▁<SUF>",
18
+ "▁<EOT>",
19
+ "▁<PRE>",
20
+ "▁<MID>",
21
+ "▁<SUF>",
22
+ "▁<EOT>"
23
+ ],
24
+ "bos_token": {
25
+ "content": "<s>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "eos_token": {
32
+ "content": "</s>",
33
+ "lstrip": false,
34
+ "normalized": true,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ "pad_token": {
39
+ "content": "</s>",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ "unk_token": {
46
+ "content": "<unk>",
47
+ "lstrip": false,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ }
52
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "32000": {
28
+ "content": "▁<PRE>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "32001": {
36
+ "content": "▁<MID>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "32002": {
44
+ "content": "▁<SUF>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "32003": {
52
+ "content": "▁<EOT>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ }
59
+ },
60
+ "additional_special_tokens": [
61
+ "▁<PRE>",
62
+ "▁<MID>",
63
+ "▁<SUF>",
64
+ "▁<EOT>",
65
+ "▁<PRE>",
66
+ "▁<MID>",
67
+ "▁<SUF>",
68
+ "▁<EOT>",
69
+ "▁<PRE>",
70
+ "▁<MID>",
71
+ "▁<SUF>",
72
+ "▁<EOT>",
73
+ "▁<PRE>",
74
+ "▁<MID>",
75
+ "▁<SUF>",
76
+ "▁<EOT>",
77
+ "▁<PRE>",
78
+ "▁<MID>",
79
+ "▁<SUF>",
80
+ "▁<EOT>"
81
+ ],
82
+ "bos_token": "<s>",
83
+ "clean_up_tokenization_spaces": false,
84
+ "eos_token": "</s>",
85
+ "eot_token": "▁<EOT>",
86
+ "fill_token": "<FILL_ME>",
87
+ "legacy": null,
88
+ "middle_token": "▁<MID>",
89
+ "model_max_length": 1024,
90
+ "pad_token": "</s>",
91
+ "prefix_token": "▁<PRE>",
92
+ "sp_model_kwargs": {},
93
+ "suffix_token": "▁<SUF>",
94
+ "tokenizer_class": "CodeLlamaTokenizer",
95
+ "unk_token": "<unk>",
96
+ "use_default_system_prompt": false
97
+ }