AlexWortega commited on
Commit
40059cd
1 Parent(s): cf72dd7

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|future_token_0|>": 79085,
3
+ "<|future_token_10|>": 79095,
4
+ "<|future_token_11|>": 79096,
5
+ "<|future_token_1|>": 79086,
6
+ "<|future_token_2|>": 79087,
7
+ "<|future_token_3|>": 79088,
8
+ "<|future_token_4|>": 79089,
9
+ "<|future_token_5|>": 79090,
10
+ "<|future_token_6|>": 79091,
11
+ "<|future_token_7|>": 79092,
12
+ "<|future_token_8|>": 79093,
13
+ "<|future_token_9|>": 79094,
14
+ "<|im_end|>": 79097,
15
+ "<|im_start|>": 79098
16
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_end|>",
4
+ "<|im_start|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<s>",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "</s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
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:e3f0f84b42f79947ab92931c7c5ded699e845e6862e4e29f0b97f87e279da601
3
+ size 1636166
tokenizer_config.json ADDED
@@ -0,0 +1,158 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
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
+ "79085": {
30
+ "content": "<|future_token_0|>",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": false
36
+ },
37
+ "79086": {
38
+ "content": "<|future_token_1|>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "79087": {
46
+ "content": "<|future_token_2|>",
47
+ "lstrip": false,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "79088": {
54
+ "content": "<|future_token_3|>",
55
+ "lstrip": false,
56
+ "normalized": true,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "79089": {
62
+ "content": "<|future_token_4|>",
63
+ "lstrip": false,
64
+ "normalized": true,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": false
68
+ },
69
+ "79090": {
70
+ "content": "<|future_token_5|>",
71
+ "lstrip": false,
72
+ "normalized": true,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": false
76
+ },
77
+ "79091": {
78
+ "content": "<|future_token_6|>",
79
+ "lstrip": false,
80
+ "normalized": true,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": false
84
+ },
85
+ "79092": {
86
+ "content": "<|future_token_7|>",
87
+ "lstrip": false,
88
+ "normalized": true,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": false
92
+ },
93
+ "79093": {
94
+ "content": "<|future_token_8|>",
95
+ "lstrip": false,
96
+ "normalized": true,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": false
100
+ },
101
+ "79094": {
102
+ "content": "<|future_token_9|>",
103
+ "lstrip": false,
104
+ "normalized": true,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": false
108
+ },
109
+ "79095": {
110
+ "content": "<|future_token_10|>",
111
+ "lstrip": false,
112
+ "normalized": true,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": false
116
+ },
117
+ "79096": {
118
+ "content": "<|future_token_11|>",
119
+ "lstrip": false,
120
+ "normalized": true,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "79097": {
126
+ "content": "<|im_end|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "79098": {
134
+ "content": "<|im_start|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": true
140
+ }
141
+ },
142
+ "additional_special_tokens": [
143
+ "<|im_end|>",
144
+ "<|im_start|>"
145
+ ],
146
+ "bos_token": "<s>",
147
+ "chat_template": "<s>{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}</s>",
148
+ "clean_up_tokenization_spaces": false,
149
+ "eos_token": "</s>",
150
+ "legacy": true,
151
+ "model_max_length": 1512,
152
+ "pad_token": "</s>",
153
+ "sp_model_kwargs": {},
154
+ "spaces_between_special_tokens": false,
155
+ "tokenizer_class": "LlamaTokenizer",
156
+ "unk_token": "<unk>",
157
+ "use_default_system_prompt": true
158
+ }