vdaita commited on
Commit
80369d5
β€’
1 Parent(s): e4ca4ac

Upload tokenizer

Browse files
special_tokens_map.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "▁<PRE>",
4
+ "▁<MID>",
5
+ "▁<SUF>",
6
+ "▁<EOT>",
7
+ "▁<PRE>",
8
+ "▁<MID>",
9
+ "▁<SUF>",
10
+ "▁<EOT>"
11
+ ],
12
+ "bos_token": {
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eos_token": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "pad_token": {
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
+ "unk_token": {
34
+ "content": "<unk>",
35
+ "lstrip": false,
36
+ "normalized": false,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ }
40
+ }
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 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "fill_token": "<FILL_ME>",
77
+ "legacy": null,
78
+ "middle_token": "▁<MID>",
79
+ "model_max_length": 16384,
80
+ "pad_token": "<unk>",
81
+ "padding_side": "left",
82
+ "prefix_token": "▁<PRE>",
83
+ "sp_model_kwargs": {},
84
+ "suffix_token": "▁<SUF>",
85
+ "tokenizer_class": "CodeLlamaTokenizer",
86
+ "unk_token": "<unk>",
87
+ "use_default_system_prompt": false
88
+ }