Hugging Face's logo

caiom
/
tokent1

Model card Files Community
caiom commited on
Commit
bb7c5c2
•
1 Parent(s): 001a13d

Upload tokenizer

Browse files
Files changed (5) hide show
  1. added_tokens.json +14 -0
  2. special_tokens_map.json +102 -0
  3. tokenizer.json +0 -0
  4. tokenizer.model +3 -0
  5. tokenizer_config.json +150 -0
added_tokens.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|assistant|>": 32005,
3
+ "<|continue|>": 32006,
4
+ "<|endoftext|>": 32000,
5
+ "<|end|>": 32001,
6
+ "<|function_call|>": 32008,
7
+ "<|function_list|>": 32007,
8
+ "<|function_output|>": 32009,
9
+ "<|raw|>": 32011,
10
+ "<|step|>": 32010,
11
+ "<|system|>": 32002,
12
+ "<|tag|>": 32003,
13
+ "<|user|>": 32004
14
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|end|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|system|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": true,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<|tag|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": true,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "<|user|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": true,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "<|assistant|>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": true,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "<|continue|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false
44
+ },
45
+ {
46
+ "content": "<|function_list|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": true,
50
+ "single_word": false
51
+ },
52
+ {
53
+ "content": "<|function_call|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": true,
57
+ "single_word": false
58
+ },
59
+ {
60
+ "content": "<|function_output|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": true,
64
+ "single_word": false
65
+ },
66
+ {
67
+ "content": "<|step|>",
68
+ "lstrip": false,
69
+ "normalized": false,
70
+ "rstrip": true,
71
+ "single_word": false
72
+ },
73
+ {
74
+ "content": "<|raw|>",
75
+ "lstrip": false,
76
+ "normalized": false,
77
+ "rstrip": true,
78
+ "single_word": false
79
+ }
80
+ ],
81
+ "bos_token": {
82
+ "content": "<s>",
83
+ "lstrip": false,
84
+ "normalized": false,
85
+ "rstrip": false,
86
+ "single_word": false
87
+ },
88
+ "eos_token": {
89
+ "content": "<|endoftext|>",
90
+ "lstrip": false,
91
+ "normalized": false,
92
+ "rstrip": false,
93
+ "single_word": false
94
+ },
95
+ "unk_token": {
96
+ "content": "<unk>",
97
+ "lstrip": false,
98
+ "normalized": false,
99
+ "rstrip": false,
100
+ "single_word": false
101
+ }
102
+ }
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,150 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 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": true,
26
+ "single_word": false,
27
+ "special": false
28
+ },
29
+ "32000": {
30
+ "content": "<|endoftext|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": true,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32002": {
46
+ "content": "<|system|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": true,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "32003": {
54
+ "content": "<|tag|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": true,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "32004": {
62
+ "content": "<|user|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": true,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "32005": {
70
+ "content": "<|assistant|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": true,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "32006": {
78
+ "content": "<|continue|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": true,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "32007": {
86
+ "content": "<|function_list|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": true,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "32008": {
94
+ "content": "<|function_call|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": true,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "32009": {
102
+ "content": "<|function_output|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": true,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "32010": {
110
+ "content": "<|step|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": true,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "32011": {
118
+ "content": "<|raw|>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": true,
122
+ "single_word": false,
123
+ "special": true
124
+ }
125
+ },
126
+ "additional_special_tokens": [
127
+ "<|end|>",
128
+ "<|system|>",
129
+ "<|tag|>",
130
+ "<|user|>",
131
+ "<|assistant|>",
132
+ "<|continue|>",
133
+ "<|function_list|>",
134
+ "<|function_call|>",
135
+ "<|function_output|>",
136
+ "<|step|>",
137
+ "<|raw|>"
138
+ ],
139
+ "bos_token": "<s>",
140
+ "clean_up_tokenization_spaces": false,
141
+ "eos_token": "<|endoftext|>",
142
+ "legacy": false,
143
+ "model_max_length": 1000000000000000019884624838656,
144
+ "pad_token": null,
145
+ "padding_side": "right",
146
+ "sp_model_kwargs": {},
147
+ "tokenizer_class": "LlamaTokenizer",
148
+ "unk_token": "<unk>",
149
+ "use_default_system_prompt": false
150
+ }