rafaelgeraldini commited on
Commit
8e6cd64
1 Parent(s): b94510d

Upload Tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +20 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +98 -0
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>",
6
+ "▁<PRE>",
7
+ "▁<SUF>",
8
+ "▁<MID>",
9
+ "▁<EOT>",
10
+ "[PAD]",
11
+ "▁<PRE>",
12
+ "▁<MID>",
13
+ "▁<SUF>",
14
+ "▁<EOT>"
15
+ ],
16
+ "bos_token": "<s>",
17
+ "eos_token": "</s>",
18
+ "pad_token": "[PAD]",
19
+ "unk_token": "<unk>"
20
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "<unk>",
70
+ "<s>",
71
+ "</s>",
72
+ "▁<PRE>",
73
+ "▁<SUF>",
74
+ "▁<MID>",
75
+ "▁<EOT>",
76
+ "[PAD]",
77
+ "▁<PRE>",
78
+ "▁<MID>",
79
+ "▁<SUF>",
80
+ "▁<EOT>"
81
+ ],
82
+ "bos_token": "<s>",
83
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content | trim + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content | trim + ' ' + eos_token }}{% endif %}{% endfor %}",
84
+ "clean_up_tokenization_spaces": false,
85
+ "eos_token": "</s>",
86
+ "eot_token": "▁<EOT>",
87
+ "fill_token": "<FILL_ME>",
88
+ "legacy": null,
89
+ "middle_token": "▁<MID>",
90
+ "model_max_length": 1000000000000000019884624838656,
91
+ "pad_token": "[PAD]",
92
+ "prefix_token": "▁<PRE>",
93
+ "sp_model_kwargs": {},
94
+ "suffix_token": "▁<SUF>",
95
+ "tokenizer_class": "CodeLlamaTokenizer",
96
+ "unk_token": "<unk>",
97
+ "use_default_system_prompt": false
98
+ }