Hugging Face's logo

mwpt5
/
solvability-checker

Feature Extraction
Transformers
Safetensors
bert
text-embeddings-inference
Inference Endpoints
Model card Files Community
yashichawla commited on
Commit
00d3280
·
1 Parent(s): 852be80

Tokenizer: Epoch 1

Browse files
Files changed (5) hide show
  1. added_tokens.json +12 -0
  2. special_tokens_map.json +19 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +147 -0
  5. vocab.txt +0 -0
added_tokens.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "N_00": 30522,
3
+ "N_01": 30523,
4
+ "N_02": 30524,
5
+ "N_03": 30525,
6
+ "N_04": 30526,
7
+ "N_05": 30527,
8
+ "N_06": 30528,
9
+ "N_07": 30529,
10
+ "N_08": 30530,
11
+ "N_09": 30531
12
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "N_00",
4
+ "N_01",
5
+ "N_02",
6
+ "N_03",
7
+ "N_04",
8
+ "N_05",
9
+ "N_06",
10
+ "N_07",
11
+ "N_08",
12
+ "N_09"
13
+ ],
14
+ "cls_token": "[CLS]",
15
+ "mask_token": "[MASK]",
16
+ "pad_token": "[PAD]",
17
+ "sep_token": "[SEP]",
18
+ "unk_token": "[UNK]"
19
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,147 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "30522": {
44
+ "content": "N_00",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "30523": {
52
+ "content": "N_01",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "30524": {
60
+ "content": "N_02",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "30525": {
68
+ "content": "N_03",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "30526": {
76
+ "content": "N_04",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "30527": {
84
+ "content": "N_05",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "30528": {
92
+ "content": "N_06",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "30529": {
100
+ "content": "N_07",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "30530": {
108
+ "content": "N_08",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "30531": {
116
+ "content": "N_09",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ }
123
+ },
124
+ "additional_special_tokens": [
125
+ "N_00",
126
+ "N_01",
127
+ "N_02",
128
+ "N_03",
129
+ "N_04",
130
+ "N_05",
131
+ "N_06",
132
+ "N_07",
133
+ "N_08",
134
+ "N_09"
135
+ ],
136
+ "clean_up_tokenization_spaces": true,
137
+ "cls_token": "[CLS]",
138
+ "do_lower_case": true,
139
+ "mask_token": "[MASK]",
140
+ "model_max_length": 1000000000000000019884624838656,
141
+ "pad_token": "[PAD]",
142
+ "sep_token": "[SEP]",
143
+ "strip_accents": null,
144
+ "tokenize_chinese_chars": true,
145
+ "tokenizer_class": "BertTokenizer",
146
+ "unk_token": "[UNK]"
147
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff