Hugging Face's logo

mi23
/
plants-morpho

Token Classification
Transformers
PyTorch
Polish
bert
Inference Endpoints
Model card Files Community
mi23 commited on
Commit
c172f37
·
1 Parent(s): 8f5cc08

Upload tokenizer

Browse files
Files changed (6) hide show
  1. added_tokens.json +17 -0
  2. merges.txt +0 -0
  3. special_tokens_map.json +20 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +148 -0
  6. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<mask>": 4,
4
+ "<pad>": 1,
5
+ "<s>": 0,
6
+ "<special0>": 50000,
7
+ "<special1>": 50001,
8
+ "<special2>": 50002,
9
+ "<special3>": 50003,
10
+ "<special4>": 50004,
11
+ "<special5>": 50005,
12
+ "<special6>": 50006,
13
+ "<special7>": 50007,
14
+ "<special8>": 50008,
15
+ "<special9>": 50009,
16
+ "<unk>": 3
17
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<special0>",
4
+ "<special1>",
5
+ "<special2>",
6
+ "<special3>",
7
+ "<special4>",
8
+ "<special5>",
9
+ "<special6>",
10
+ "<special7>",
11
+ "<special8>",
12
+ "<special9>"
13
+ ],
14
+ "bos_token": "<s>",
15
+ "cls_token": "<s>",
16
+ "mask_token": "<mask>",
17
+ "pad_token": "<pad>",
18
+ "sep_token": "</s>",
19
+ "unk_token": "<unk>"
20
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,148 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "50000": {
44
+ "content": "<special0>",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": true,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "50001": {
52
+ "content": "<special1>",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": true,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "50002": {
60
+ "content": "<special2>",
61
+ "lstrip": true,
62
+ "normalized": false,
63
+ "rstrip": true,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "50003": {
68
+ "content": "<special3>",
69
+ "lstrip": true,
70
+ "normalized": false,
71
+ "rstrip": true,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "50004": {
76
+ "content": "<special4>",
77
+ "lstrip": true,
78
+ "normalized": false,
79
+ "rstrip": true,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "50005": {
84
+ "content": "<special5>",
85
+ "lstrip": true,
86
+ "normalized": false,
87
+ "rstrip": true,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "50006": {
92
+ "content": "<special6>",
93
+ "lstrip": true,
94
+ "normalized": false,
95
+ "rstrip": true,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "50007": {
100
+ "content": "<special7>",
101
+ "lstrip": true,
102
+ "normalized": false,
103
+ "rstrip": true,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "50008": {
108
+ "content": "<special8>",
109
+ "lstrip": true,
110
+ "normalized": false,
111
+ "rstrip": true,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "50009": {
116
+ "content": "<special9>",
117
+ "lstrip": true,
118
+ "normalized": false,
119
+ "rstrip": true,
120
+ "single_word": false,
121
+ "special": true
122
+ }
123
+ },
124
+ "additional_special_tokens": [
125
+ "<special0>",
126
+ "<special1>",
127
+ "<special2>",
128
+ "<special3>",
129
+ "<special4>",
130
+ "<special5>",
131
+ "<special6>",
132
+ "<special7>",
133
+ "<special8>",
134
+ "<special9>"
135
+ ],
136
+ "bos_token": "<s>",
137
+ "clean_up_tokenization_spaces": true,
138
+ "cls_token": "<s>",
139
+ "do_lowercase_and_remove_accent": false,
140
+ "id2lang": null,
141
+ "lang2id": null,
142
+ "mask_token": "<mask>",
143
+ "model_max_length": 512,
144
+ "pad_token": "<pad>",
145
+ "sep_token": "</s>",
146
+ "tokenizer_class": "HerbertTokenizer",
147
+ "unk_token": "<unk>"
148
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff