stangirala commited on
Commit
4cd2592
Β·
1 Parent(s): fe5313c

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<s>": 1,
4
+ "<unk>": 0,
5
+ "▁<EOT>": 32010,
6
+ "▁<MID>": 32009,
7
+ "▁<PRE>": 32007,
8
+ "▁<SUF>": 32008
9
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>",
6
+ "▁<PRE>",
7
+ "▁<SUF>",
8
+ "▁<MID>",
9
+ "▁<EOT>",
10
+ "▁<PRE>",
11
+ "▁<MID>",
12
+ "▁<SUF>",
13
+ "▁<EOT>"
14
+ ],
15
+ "bos_token": "<s>",
16
+ "eos_token": "</s>",
17
+ "pad_token": "</s>",
18
+ "unk_token": "<unk>"
19
+ }
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 sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
3
+ size 500058
tokenizer_config.json ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32007": {
30
+ "content": "▁<PRE>",
31
+ "lstrip": true,
32
+ "normalized": false,
33
+ "rstrip": true,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32008": {
38
+ "content": "▁<SUF>",
39
+ "lstrip": true,
40
+ "normalized": false,
41
+ "rstrip": true,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32009": {
46
+ "content": "▁<MID>",
47
+ "lstrip": true,
48
+ "normalized": false,
49
+ "rstrip": true,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "32010": {
54
+ "content": "▁<EOT>",
55
+ "lstrip": true,
56
+ "normalized": false,
57
+ "rstrip": true,
58
+ "single_word": false,
59
+ "special": true
60
+ }
61
+ },
62
+ "additional_special_tokens": [
63
+ "<unk>",
64
+ "<s>",
65
+ "</s>",
66
+ "▁<PRE>",
67
+ "▁<SUF>",
68
+ "▁<MID>",
69
+ "▁<EOT>",
70
+ "▁<PRE>",
71
+ "▁<MID>",
72
+ "▁<SUF>",
73
+ "▁<EOT>"
74
+ ],
75
+ "bos_token": "<s>",
76
+ "clean_up_tokenization_spaces": false,
77
+ "eos_token": "</s>",
78
+ "eot_token": "▁<EOT>",
79
+ "fill_token": "<FILL_ME>",
80
+ "legacy": null,
81
+ "middle_token": "▁<MID>",
82
+ "model_max_length": 1000000000000000019884624838656,
83
+ "pad_token": "</s>",
84
+ "prefix_token": "▁<PRE>",
85
+ "sp_model_kwargs": {},
86
+ "suffix_first": false,
87
+ "suffix_token": "▁<SUF>",
88
+ "tokenizer_class": "CodeLlamaTokenizer",
89
+ "trust_remote_code": false,
90
+ "unk_token": "<unk>",
91
+ "use_default_system_prompt": false,
92
+ "use_fast": true
93
+ }