Hugging Face's logo

text2tech
/
REBEL_NER_RE_001_1000docs

Transformers
Safetensors
bart
text2text-generation
Model card Files
xet
Community
Matthias Meyer commited on
Commit
a54d7b0
·
verified ·
1 Parent(s): 98f768a

Upload tokenizer

Browse files
Files changed (6) hide show
  1. added_tokens.json +14 -0
  2. merges.txt +0 -0
  3. special_tokens_map.json +60 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +162 -0
  6. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</head>": 50269,
3
+ "</tail>": 50271,
4
+ "<head>": 50268,
5
+ "<mat>": 50272,
6
+ "<meth>": 50273,
7
+ "<obj>": 50265,
8
+ "<org>": 50275,
9
+ "<subj>": 50266,
10
+ "<tail>": 50270,
11
+ "<tfield>": 50276,
12
+ "<triplet>": 50267,
13
+ "<tsys>": 50274
14
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<obj>",
4
+ "<subj>",
5
+ "<triplet>",
6
+ "<head>",
7
+ "</head>",
8
+ "<tail>",
9
+ "</tail>"
10
+ ],
11
+ "bos_token": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "cls_token": {
19
+ "content": "<s>",
20
+ "lstrip": false,
21
+ "normalized": true,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "eos_token": {
26
+ "content": "</s>",
27
+ "lstrip": false,
28
+ "normalized": true,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "mask_token": {
33
+ "content": "<mask>",
34
+ "lstrip": true,
35
+ "normalized": true,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ },
39
+ "pad_token": {
40
+ "content": "<pad>",
41
+ "lstrip": false,
42
+ "normalized": true,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "sep_token": {
47
+ "content": "</s>",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ },
53
+ "unk_token": {
54
+ "content": "<unk>",
55
+ "lstrip": false,
56
+ "normalized": true,
57
+ "rstrip": false,
58
+ "single_word": false
59
+ }
60
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,162 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "50265": {
45
+ "content": "<obj>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "50266": {
53
+ "content": "<subj>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "50267": {
61
+ "content": "<triplet>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "50268": {
69
+ "content": "<head>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "50269": {
77
+ "content": "</head>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "50270": {
85
+ "content": "<tail>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "50271": {
93
+ "content": "</tail>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "50272": {
101
+ "content": "<mat>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "50273": {
109
+ "content": "<meth>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "50274": {
117
+ "content": "<tsys>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "50275": {
125
+ "content": "<org>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "50276": {
133
+ "content": "<tfield>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ }
140
+ },
141
+ "additional_special_tokens": [
142
+ "<obj>",
143
+ "<subj>",
144
+ "<triplet>",
145
+ "<head>",
146
+ "</head>",
147
+ "<tail>",
148
+ "</tail>"
149
+ ],
150
+ "bos_token": "<s>",
151
+ "clean_up_tokenization_spaces": true,
152
+ "cls_token": "<s>",
153
+ "eos_token": "</s>",
154
+ "errors": "replace",
155
+ "mask_token": "<mask>",
156
+ "model_max_length": 1024,
157
+ "pad_token": "<pad>",
158
+ "sep_token": "</s>",
159
+ "tokenizer_class": "BartTokenizer",
160
+ "trim_offsets": true,
161
+ "unk_token": "<unk>"
162
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff