Hugging Face's logo

jounce
/
dummy-phi3

Safetensors
phi3
Model card Files
xet
Community
AlonKellner-Jounce commited on
Commit
6f5df4c
·
verified ·
1 Parent(s): 234f2b0

dummy-phi3 recreated

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +51 -1
  2. tokenizer.json +185 -1
  3. tokenizer_config.json +58 -1
special_tokens_map.json CHANGED
@@ -1 +1,51 @@
1
- {"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json CHANGED
@@ -1 +1,185 @@
1
- {"version":"1.0","truncation":null,"padding":{"strategy":{"Fixed":10},"direction":"Right","pad_to_multiple_of":null,"pad_id":3,"pad_type_id":0,"pad_token":"[PAD]"},"added_tokens":[{"id":0,"special":true,"content":"[UNK]","single_word":false,"lstrip":false,"rstrip":false,"normalized":false},{"id":1,"special":true,"content":"[CLS]","single_word":false,"lstrip":false,"rstrip":false,"normalized":false},{"id":2,"special":true,"content":"[SEP]","single_word":false,"lstrip":false,"rstrip":false,"normalized":false},{"id":3,"special":true,"content":"[PAD]","single_word":false,"lstrip":false,"rstrip":false,"normalized":false},{"id":4,"special":true,"content":"[MASK]","single_word":false,"lstrip":false,"rstrip":false,"normalized":false}],"normalizer":{"type":"Sequence","normalizers":[{"type":"NFD"},{"type":"Lowercase"},{"type":"StripAccents"}]},"pre_tokenizer":{"type":"Sequence","pretokenizers":[{"type":"Whitespace"},{"type":"Digits","individual_digits":true}]},"post_processor":{"type":"TemplateProcessing","single":[{"SpecialToken":{"id":"[CLS]","type_id":0}},{"Sequence":{"id":"A","type_id":0}},{"SpecialToken":{"id":"[SEP]","type_id":0}}],"pair":[{"SpecialToken":{"id":"[CLS]","type_id":0}},{"Sequence":{"id":"A","type_id":0}},{"SpecialToken":{"id":"[SEP]","type_id":0}},{"Sequence":{"id":"B","type_id":1}},{"SpecialToken":{"id":"[SEP]","type_id":1}}],"special_tokens":{"[CLS]":{"id":"[CLS]","ids":[1],"tokens":["[CLS]"]},"[SEP]":{"id":"[SEP]","ids":[2],"tokens":["[SEP]"]}}},"decoder":null,"model":{"type":"WordLevel","vocab":{"[UNK]":0,"[CLS]":1,"[SEP]":2,"[PAD]":3,"[MASK]":4,".":5,"this":6,"sentence":7,"is":8,"one":9,"the":10,"2":11,"#)":12,"3":13,"numbers":14,"symbols":15,"first":16,"contains":17,"1":18,"not":19,"but":20,"second":21,"(":22,"and":23,"over":24},"unk_token":"[UNK]"}}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "[UNK]",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "[CLS]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "[SEP]",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "[PAD]",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 4,
44
+ "content": "[MASK]",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ }
51
+ ],
52
+ "normalizer": {
53
+ "type": "Sequence",
54
+ "normalizers": [
55
+ {
56
+ "type": "NFD"
57
+ },
58
+ {
59
+ "type": "Lowercase"
60
+ },
61
+ {
62
+ "type": "StripAccents"
63
+ }
64
+ ]
65
+ },
66
+ "pre_tokenizer": {
67
+ "type": "Sequence",
68
+ "pretokenizers": [
69
+ {
70
+ "type": "Whitespace"
71
+ },
72
+ {
73
+ "type": "Digits",
74
+ "individual_digits": true
75
+ }
76
+ ]
77
+ },
78
+ "post_processor": {
79
+ "type": "TemplateProcessing",
80
+ "single": [
81
+ {
82
+ "SpecialToken": {
83
+ "id": "[CLS]",
84
+ "type_id": 0
85
+ }
86
+ },
87
+ {
88
+ "Sequence": {
89
+ "id": "A",
90
+ "type_id": 0
91
+ }
92
+ },
93
+ {
94
+ "SpecialToken": {
95
+ "id": "[SEP]",
96
+ "type_id": 0
97
+ }
98
+ }
99
+ ],
100
+ "pair": [
101
+ {
102
+ "SpecialToken": {
103
+ "id": "[CLS]",
104
+ "type_id": 0
105
+ }
106
+ },
107
+ {
108
+ "Sequence": {
109
+ "id": "A",
110
+ "type_id": 0
111
+ }
112
+ },
113
+ {
114
+ "SpecialToken": {
115
+ "id": "[SEP]",
116
+ "type_id": 0
117
+ }
118
+ },
119
+ {
120
+ "Sequence": {
121
+ "id": "B",
122
+ "type_id": 1
123
+ }
124
+ },
125
+ {
126
+ "SpecialToken": {
127
+ "id": "[SEP]",
128
+ "type_id": 1
129
+ }
130
+ }
131
+ ],
132
+ "special_tokens": {
133
+ "[CLS]": {
134
+ "id": "[CLS]",
135
+ "ids": [
136
+ 1
137
+ ],
138
+ "tokens": [
139
+ "[CLS]"
140
+ ]
141
+ },
142
+ "[SEP]": {
143
+ "id": "[SEP]",
144
+ "ids": [
145
+ 2
146
+ ],
147
+ "tokens": [
148
+ "[SEP]"
149
+ ]
150
+ }
151
+ }
152
+ },
153
+ "decoder": null,
154
+ "model": {
155
+ "type": "WordLevel",
156
+ "vocab": {
157
+ "[UNK]": 0,
158
+ "[CLS]": 1,
159
+ "[SEP]": 2,
160
+ "[PAD]": 3,
161
+ "[MASK]": 4,
162
+ ".": 5,
163
+ "this": 6,
164
+ "sentence": 7,
165
+ "is": 8,
166
+ "one": 9,
167
+ "the": 10,
168
+ "2": 11,
169
+ "#)": 12,
170
+ "3": 13,
171
+ "numbers": 14,
172
+ "symbols": 15,
173
+ "first": 16,
174
+ "contains": 17,
175
+ "1": 18,
176
+ "not": 19,
177
+ "but": 20,
178
+ "second": 21,
179
+ "(": 22,
180
+ "and": 23,
181
+ "over": 24
182
+ },
183
+ "unk_token": "[UNK]"
184
+ }
185
+ }
tokenizer_config.json CHANGED
@@ -1 +1,58 @@
1
- {"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "model_max_length": 10, "padding_side": "right", "tokenizer_class": "PreTrainedTokenizerFast"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[UNK]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[PAD]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "[CLS]",
47
+ "eos_token": "[SEP]",
48
+ "mask_token": "[MASK]",
49
+ "max_length": 10,
50
+ "model_max_length": 10,
51
+ "pad_to_multiple_of": null,
52
+ "pad_token": "[PAD]",
53
+ "pad_token_type_id": 0,
54
+ "padding_side": "right",
55
+ "sep_token": "[SEP]",
56
+ "tokenizer_class": "PreTrainedTokenizerFast",
57
+ "unk_token": "[UNK]"
58
+ }