Hugging Face's logo

Sowrabhm
/
fintext-extractor

Token Classification
ONNX
GLiNER2
English
onnxruntime
ner
transaction-extraction
sms-parsing
deberta
on-device
mobile
Model card Files
xet
Community
Sowrabhm commited on
Commit
2da162c
·
verified ·
1 Parent(s): b0e098b

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. tokenizer_extraction/added_tokens.json +13 -0
  2. tokenizer_extraction/special_tokens_map.json +123 -0
  3. tokenizer_extraction/spm.model +3 -0
  4. tokenizer_extraction/tokenizer.json +0 -0
  5. tokenizer_extraction/tokenizer_config.json +151 -0
tokenizer_extraction/added_tokens.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[C]": 128004,
3
+ "[DESCRIPTION]": 128010,
4
+ "[EXAMPLE]": 128008,
5
+ "[E]": 128005,
6
+ "[L]": 128007,
7
+ "[MASK]": 128000,
8
+ "[OUTPUT]": 128009,
9
+ "[P]": 128003,
10
+ "[R]": 128006,
11
+ "[SEP_STRUCT]": 128001,
12
+ "[SEP_TEXT]": 128002
13
+ }
tokenizer_extraction/special_tokens_map.json ADDED
@@ -0,0 +1,123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "[SEP_STRUCT]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "[SEP_TEXT]",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "[P]",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "[C]",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "[E]",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "[R]",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ {
46
+ "content": "[L]",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ {
53
+ "content": "[EXAMPLE]",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ },
59
+ {
60
+ "content": "[OUTPUT]",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ {
67
+ "content": "[DESCRIPTION]",
68
+ "lstrip": false,
69
+ "normalized": false,
70
+ "rstrip": false,
71
+ "single_word": false
72
+ }
73
+ ],
74
+ "bos_token": {
75
+ "content": "[CLS]",
76
+ "lstrip": false,
77
+ "normalized": false,
78
+ "rstrip": false,
79
+ "single_word": false
80
+ },
81
+ "cls_token": {
82
+ "content": "[CLS]",
83
+ "lstrip": false,
84
+ "normalized": false,
85
+ "rstrip": false,
86
+ "single_word": false
87
+ },
88
+ "eos_token": {
89
+ "content": "[SEP]",
90
+ "lstrip": false,
91
+ "normalized": false,
92
+ "rstrip": false,
93
+ "single_word": false
94
+ },
95
+ "mask_token": {
96
+ "content": "[MASK]",
97
+ "lstrip": false,
98
+ "normalized": false,
99
+ "rstrip": false,
100
+ "single_word": false
101
+ },
102
+ "pad_token": {
103
+ "content": "[PAD]",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false
108
+ },
109
+ "sep_token": {
110
+ "content": "[SEP]",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false
115
+ },
116
+ "unk_token": {
117
+ "content": "[UNK]",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false
122
+ }
123
+ }
tokenizer_extraction/spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
tokenizer_extraction/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_extraction/tokenizer_config.json ADDED
@@ -0,0 +1,151 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "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": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128000": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128001": {
44
+ "content": "[SEP_STRUCT]",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128002": {
52
+ "content": "[SEP_TEXT]",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128003": {
60
+ "content": "[P]",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128004": {
68
+ "content": "[C]",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128005": {
76
+ "content": "[E]",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128006": {
84
+ "content": "[R]",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128007": {
92
+ "content": "[L]",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128008": {
100
+ "content": "[EXAMPLE]",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128009": {
108
+ "content": "[OUTPUT]",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128010": {
116
+ "content": "[DESCRIPTION]",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ }
123
+ },
124
+ "additional_special_tokens": [
125
+ "[SEP_STRUCT]",
126
+ "[SEP_TEXT]",
127
+ "[P]",
128
+ "[C]",
129
+ "[E]",
130
+ "[R]",
131
+ "[L]",
132
+ "[EXAMPLE]",
133
+ "[OUTPUT]",
134
+ "[DESCRIPTION]"
135
+ ],
136
+ "bos_token": "[CLS]",
137
+ "clean_up_tokenization_spaces": false,
138
+ "cls_token": "[CLS]",
139
+ "do_lower_case": false,
140
+ "eos_token": "[SEP]",
141
+ "extra_special_tokens": {},
142
+ "mask_token": "[MASK]",
143
+ "model_max_length": 1000000000000000019884624838656,
144
+ "pad_token": "[PAD]",
145
+ "sep_token": "[SEP]",
146
+ "sp_model_kwargs": {},
147
+ "split_by_punct": false,
148
+ "tokenizer_class": "DebertaV2Tokenizer",
149
+ "unk_token": "[UNK]",
150
+ "vocab_type": "spm"
151
+ }