Hugging Face's logo

empty-michael
/
cfg4.4-small

Text Generation
Transformers
Safetensors
llama
text-generation-inference
Inference Endpoints
Model card Files Community
empty-michael commited on
Commit
8c3ba5e
•
1 Parent(s): 3593c37

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +6 -0
  2. tokenizer.json +141 -0
  3. tokenizer_config.json +43 -0
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "mask_token": "[MASK]",
3
+ "pad_token": "0",
4
+ "sep_token": "[SEP]",
5
+ "unk_token": "[UNK]"
6
+ }
tokenizer.json ADDED
@@ -0,0 +1,141 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 5,
8
+ "content": "[UNK]",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 6,
17
+ "content": "[SEP]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 7,
26
+ "content": "0",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 8,
35
+ "content": "[MASK]",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ }
42
+ ],
43
+ "normalizer": null,
44
+ "pre_tokenizer": {
45
+ "type": "Digits",
46
+ "individual_digits": true
47
+ },
48
+ "post_processor": {
49
+ "type": "TemplateProcessing",
50
+ "single": [
51
+ {
52
+ "SpecialToken": {
53
+ "id": "<s>",
54
+ "type_id": 0
55
+ }
56
+ },
57
+ {
58
+ "Sequence": {
59
+ "id": "A",
60
+ "type_id": 0
61
+ }
62
+ },
63
+ {
64
+ "SpecialToken": {
65
+ "id": "</s>",
66
+ "type_id": 0
67
+ }
68
+ }
69
+ ],
70
+ "pair": [
71
+ {
72
+ "SpecialToken": {
73
+ "id": "<s>",
74
+ "type_id": 0
75
+ }
76
+ },
77
+ {
78
+ "Sequence": {
79
+ "id": "A",
80
+ "type_id": 0
81
+ }
82
+ },
83
+ {
84
+ "SpecialToken": {
85
+ "id": "</s>",
86
+ "type_id": 0
87
+ }
88
+ },
89
+ {
90
+ "SpecialToken": {
91
+ "id": "<s>",
92
+ "type_id": 0
93
+ }
94
+ },
95
+ {
96
+ "Sequence": {
97
+ "id": "B",
98
+ "type_id": 0
99
+ }
100
+ },
101
+ {
102
+ "SpecialToken": {
103
+ "id": "</s>",
104
+ "type_id": 0
105
+ }
106
+ }
107
+ ],
108
+ "special_tokens": {
109
+ "</s>": {
110
+ "id": "</s>",
111
+ "ids": [
112
+ 7
113
+ ],
114
+ "tokens": [
115
+ "</s>"
116
+ ]
117
+ },
118
+ "<s>": {
119
+ "id": "<s>",
120
+ "ids": [
121
+ 6
122
+ ],
123
+ "tokens": [
124
+ "<s>"
125
+ ]
126
+ }
127
+ }
128
+ },
129
+ "decoder": null,
130
+ "model": {
131
+ "type": "WordLevel",
132
+ "vocab": {
133
+ "1": 1,
134
+ "2": 2,
135
+ "3": 3,
136
+ "4": 4,
137
+ "5": 5
138
+ },
139
+ "unk_token": "<unk>"
140
+ }
141
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "5": {
4
+ "content": "[UNK]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "6": {
12
+ "content": "[SEP]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "7": {
20
+ "content": "0",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "8": {
28
+ "content": "[MASK]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "clean_up_tokenization_spaces": true,
37
+ "mask_token": "[MASK]",
38
+ "model_max_length": 1000000000000000019884624838656,
39
+ "pad_token": "0",
40
+ "sep_token": "[SEP]",
41
+ "tokenizer_class": "PreTrainedTokenizerFast",
42
+ "unk_token": "[UNK]"
43
+ }