RichardErkhov commited on
Commit
9f7798a
·
verified ·
1 Parent(s): 206a746

uploaded model

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +138 -0
tokenizer_config.json ADDED
@@ -0,0 +1,138 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<|startoftext|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "<|endoftext|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "6": {
31
+ "content": "<|im_start|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "7": {
39
+ "content": "<|im_end|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "64000": {
47
+ "content": "<|next_start|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "64001": {
55
+ "content": "<|next_end|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "64002": {
63
+ "content": "<|target_start|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "64003": {
71
+ "content": "<|target_end|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "64004": {
79
+ "content": "<|target|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "64005": {
87
+ "content": "<|search_and_replace|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ }
94
+ },
95
+ "additional_special_tokens": [
96
+ "<|im_start|>",
97
+ "<|im_end|>",
98
+ "<|next_start|>",
99
+ "<|next_end|>",
100
+ "<|target_start|>",
101
+ "<|target_end|>",
102
+ "<|target|>",
103
+ "<|search_and_replace|>"
104
+ ],
105
+ "bos_token": "<|startoftext|>",
106
+ "chat_template": [
107
+ {
108
+ "name": "default",
109
+ "template": "{% for message in messages %}{% if loop.first and message['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful programming assistant.<|im_end|>\n' }}{% endif %}{% if not loop.first %}{{ '\n' }}{% endif %}{{ '<|im_start|>' + message['role'] }}{% if 'name' in message %}{{ ' name=' + message['name'] }}{% endif %}{{ '\n' + message['content'] + '<|im_end|>' }}{% if loop.last and add_generation_prompt %}{{ '\n<|im_start|>assistant\n' }}{% endif %}{% endfor %}"
110
+ },
111
+ {
112
+ "name": "assistant-conversation",
113
+ "template": "{% for message in messages %}{% if loop.first and message['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful programming assistant.<|im_end|>\n' }}{% endif %}{% if not loop.first %}{{ '\n' }}{% endif %}{{ '<|im_start|>' + message['role'] }}{% if 'name' in message %}{{ ' name=' + message['name'] }}{% endif %}{{ '\n' + message['content'] + '<|im_end|>' }}{% if loop.last and add_generation_prompt %}{{ '\n<|im_start|>assistant\n<|next_start|>' }}{% endif %}{% endfor %}"
114
+ },
115
+ {
116
+ "name": "prefix_response",
117
+ "template": "{% for message in messages %}{% if loop.first and message['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful programming assistant.<|im_end|>\n' }}{% endif %}{% if not loop.first %}{{ '\n' }}{% endif %}{{ '<|im_start|>' + message['role'] }}{% if 'name' in message %}{{ ' name=' + message['name'] }}{% endif %}{{ '\n' + message['content'] }}{% if not loop.last %}{{ '<|im_end|>' }}{% endif %}{% endfor %}"
118
+ }
119
+ ],
120
+ "clean_up_tokenization_spaces": false,
121
+ "eos_token": "<|im_end|>",
122
+ "extra_special_tokens": {},
123
+ "legacy": true,
124
+ "max_length": 16384,
125
+ "model_max_length": 16384,
126
+ "pad_to_multiple_of": null,
127
+ "pad_token": "<|endoftext|>",
128
+ "pad_token_type_id": 0,
129
+ "padding_side": "left",
130
+ "sp_model_kwargs": {},
131
+ "spaces_between_special_tokens": false,
132
+ "stride": 0,
133
+ "tokenizer_class": "LlamaTokenizer",
134
+ "truncation_side": "right",
135
+ "truncation_strategy": "longest_first",
136
+ "unk_token": "<unk>",
137
+ "use_default_system_prompt": false
138
+ }