Hugging Face's logo

grascii
/
gregg-vision-v0.2.1

Image-to-Text
Transformers
Safetensors
vision-encoder-decoder
image-text-to-text
gregg
shorthand
stenography
Inference Endpoints
Model card Files Community
1
chanicpanic commited on
Commit
152453e
·
verified ·
1 Parent(s): ccc98cc

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +9 -0
  2. tokenizer.json +145 -0
  3. tokenizer_config.json +52 -0
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "pad_token": {
3
+ "content": "<pad>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ }
9
+ }
tokenizer.json ADDED
@@ -0,0 +1,145 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": {
5
+ "strategy": {
6
+ "Fixed": 12
7
+ },
8
+ "direction": "Right",
9
+ "pad_to_multiple_of": null,
10
+ "pad_id": 1,
11
+ "pad_type_id": 0,
12
+ "pad_token": "<pad>"
13
+ },
14
+ "added_tokens": [
15
+ {
16
+ "id": 0,
17
+ "content": "<s>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 1,
26
+ "content": "<pad>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 2,
35
+ "content": "</s>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 3,
44
+ "content": "<unk>",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 4,
53
+ "content": "<mask>",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
+ }
60
+ ],
61
+ "normalizer": {
62
+ "type": "Replace",
63
+ "pattern": {
64
+ "String": "X"
65
+ },
66
+ "content": "S"
67
+ },
68
+ "pre_tokenizer": {
69
+ "type": "Split",
70
+ "pattern": {
71
+ "String": "-"
72
+ },
73
+ "behavior": "Removed",
74
+ "invert": false
75
+ },
76
+ "post_processor": {
77
+ "type": "RobertaProcessing",
78
+ "sep": [
79
+ "</s>",
80
+ 2
81
+ ],
82
+ "cls": [
83
+ "<s>",
84
+ 0
85
+ ],
86
+ "trim_offsets": true,
87
+ "add_prefix_space": false
88
+ },
89
+ "decoder": {
90
+ "type": "Fuse"
91
+ },
92
+ "model": {
93
+ "type": "WordLevel",
94
+ "vocab": {
95
+ "<s>": 0,
96
+ "<pad>": 1,
97
+ "</s>": 2,
98
+ "<unk>": 3,
99
+ "<mask>": 4,
100
+ "E": 5,
101
+ "S": 6,
102
+ "R": 7,
103
+ "A": 8,
104
+ "K": 9,
105
+ "L": 10,
106
+ "N": 11,
107
+ "T": 12,
108
+ "O": 13,
109
+ "P": 14,
110
+ "M": 15,
111
+ "^": 16,
112
+ "U": 17,
113
+ "B": 18,
114
+ "D": 19,
115
+ "SH": 20,
116
+ "F": 21,
117
+ "V": 22,
118
+ "I": 23,
119
+ "G": 24,
120
+ "J": 25,
121
+ "NT": 26,
122
+ "'": 27,
123
+ "TN": 28,
124
+ "MN": 29,
125
+ "TH": 30,
126
+ "CH": 31,
127
+ "EU": 32,
128
+ "TM": 33,
129
+ "DF": 34,
130
+ "A&'": 35,
131
+ "OE": 36,
132
+ "SS": 37,
133
+ "NG": 38,
134
+ "NK": 39,
135
+ "AU": 40,
136
+ "TD": 41,
137
+ "PNT": 42,
138
+ "A&E": 43,
139
+ "LD": 44,
140
+ "MT": 45,
141
+ "\\": 46
142
+ },
143
+ "unk_token": "<unk>"
144
+ }
145
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
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
+ "clean_up_tokenization_spaces": true,
45
+ "model_input_names": [
46
+ "labels",
47
+ "pixel_values"
48
+ ],
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "pad_token": "<pad>",
51
+ "tokenizer_class": "PreTrainedTokenizerFast"
52
+ }