Fmuaddib commited on
Commit
87e069f
·
verified ·
1 Parent(s): af088c9

Upload tokenizer_config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +101 -0
tokenizer_config.json ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "3": {
31
+ "content": "[INST]",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "4": {
39
+ "content": "[/INST]",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "5": {
47
+ "content": "[TOOL_CALLS]",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "6": {
55
+ "content": "[AVAILABLE_TOOLS]",
56
+ "lstrip": false,
57
+ "normalized": true,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "7": {
63
+ "content": "[/AVAILABLE_TOOLS]",
64
+ "lstrip": false,
65
+ "normalized": true,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "9": {
71
+ "content": "[/TOOL_RESULTS]",
72
+ "lstrip": false,
73
+ "normalized": true,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32768": {
79
+ "content": "[TOOL_RESULT]",
80
+ "lstrip": false,
81
+ "normalized": true,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ }
86
+ },
87
+ "additional_special_tokens": [],
88
+ "bos_token": "<s>",
89
+ "chat_template": "{{bos_token}}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ ' [INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + message['content'] + ' ' + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
90
+ "clean_up_tokenization_spaces": false,
91
+ "eos_token": "</s>",
92
+ "extra_special_tokens": {},
93
+ "legacy": true,
94
+ "model_max_length": 1000000000000000019884624838656,
95
+ "pad_token": null,
96
+ "sp_model_kwargs": {},
97
+ "spaces_between_special_tokens": false,
98
+ "tokenizer_class": "LlamaTokenizerFast",
99
+ "unk_token": "<unk>",
100
+ "use_default_system_prompt": false
101
+ }