Hugging Face's logo

Den4ikAI
/
umt5-small-ruen

Text2Text Generation
Transformers
Safetensors
t5
text-generation-inference
Inference Endpoints
Model card Files Community
Den4ikAI commited on
Commit
6a392d2
·
verified ·
1 Parent(s): 07a0800

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +22 -0
  2. special_tokens_map.json +45 -0
  3. spiece.model +3 -0
  4. tokenizer_config.json +220 -0
added_tokens.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<extra_id_0>": 33664,
3
+ "<extra_id_10>": 33654,
4
+ "<extra_id_11>": 33653,
5
+ "<extra_id_12>": 33652,
6
+ "<extra_id_13>": 33651,
7
+ "<extra_id_14>": 33650,
8
+ "<extra_id_15>": 33649,
9
+ "<extra_id_16>": 33648,
10
+ "<extra_id_17>": 33647,
11
+ "<extra_id_18>": 33646,
12
+ "<extra_id_19>": 33645,
13
+ "<extra_id_1>": 33663,
14
+ "<extra_id_2>": 33662,
15
+ "<extra_id_3>": 33661,
16
+ "<extra_id_4>": 33660,
17
+ "<extra_id_5>": 33659,
18
+ "<extra_id_6>": 33658,
19
+ "<extra_id_7>": 33657,
20
+ "<extra_id_8>": 33656,
21
+ "<extra_id_9>": 33655
22
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>"
23
+ ],
24
+ "eos_token": {
25
+ "content": "</s>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "pad_token": {
32
+ "content": "<pad>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ "unk_token": {
39
+ "content": "<unk>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ }
45
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9e25ea0d788361e001072bb2a733ba335a20cec77d641a001bde5e18dbca178
3
+ size 727204
tokenizer_config.json ADDED
@@ -0,0 +1,220 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "3": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "33645": {
29
+ "content": "<extra_id_19>",
30
+ "lstrip": true,
31
+ "normalized": false,
32
+ "rstrip": true,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "33646": {
37
+ "content": "<extra_id_18>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": true,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "33647": {
45
+ "content": "<extra_id_17>",
46
+ "lstrip": true,
47
+ "normalized": false,
48
+ "rstrip": true,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "33648": {
53
+ "content": "<extra_id_16>",
54
+ "lstrip": true,
55
+ "normalized": false,
56
+ "rstrip": true,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "33649": {
61
+ "content": "<extra_id_15>",
62
+ "lstrip": true,
63
+ "normalized": false,
64
+ "rstrip": true,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "33650": {
69
+ "content": "<extra_id_14>",
70
+ "lstrip": true,
71
+ "normalized": false,
72
+ "rstrip": true,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "33651": {
77
+ "content": "<extra_id_13>",
78
+ "lstrip": true,
79
+ "normalized": false,
80
+ "rstrip": true,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "33652": {
85
+ "content": "<extra_id_12>",
86
+ "lstrip": true,
87
+ "normalized": false,
88
+ "rstrip": true,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "33653": {
93
+ "content": "<extra_id_11>",
94
+ "lstrip": true,
95
+ "normalized": false,
96
+ "rstrip": true,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "33654": {
101
+ "content": "<extra_id_10>",
102
+ "lstrip": true,
103
+ "normalized": false,
104
+ "rstrip": true,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "33655": {
109
+ "content": "<extra_id_9>",
110
+ "lstrip": true,
111
+ "normalized": false,
112
+ "rstrip": true,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "33656": {
117
+ "content": "<extra_id_8>",
118
+ "lstrip": true,
119
+ "normalized": false,
120
+ "rstrip": true,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "33657": {
125
+ "content": "<extra_id_7>",
126
+ "lstrip": true,
127
+ "normalized": false,
128
+ "rstrip": true,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "33658": {
133
+ "content": "<extra_id_6>",
134
+ "lstrip": true,
135
+ "normalized": false,
136
+ "rstrip": true,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "33659": {
141
+ "content": "<extra_id_5>",
142
+ "lstrip": true,
143
+ "normalized": false,
144
+ "rstrip": true,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "33660": {
149
+ "content": "<extra_id_4>",
150
+ "lstrip": true,
151
+ "normalized": false,
152
+ "rstrip": true,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "33661": {
157
+ "content": "<extra_id_3>",
158
+ "lstrip": true,
159
+ "normalized": false,
160
+ "rstrip": true,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "33662": {
165
+ "content": "<extra_id_2>",
166
+ "lstrip": true,
167
+ "normalized": false,
168
+ "rstrip": true,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "33663": {
173
+ "content": "<extra_id_1>",
174
+ "lstrip": true,
175
+ "normalized": false,
176
+ "rstrip": true,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "33664": {
181
+ "content": "<extra_id_0>",
182
+ "lstrip": true,
183
+ "normalized": false,
184
+ "rstrip": true,
185
+ "single_word": false,
186
+ "special": true
187
+ }
188
+ },
189
+ "additional_special_tokens": [
190
+ "<extra_id_0>",
191
+ "<extra_id_1>",
192
+ "<extra_id_2>",
193
+ "<extra_id_3>",
194
+ "<extra_id_4>",
195
+ "<extra_id_5>",
196
+ "<extra_id_6>",
197
+ "<extra_id_7>",
198
+ "<extra_id_8>",
199
+ "<extra_id_9>",
200
+ "<extra_id_10>",
201
+ "<extra_id_11>",
202
+ "<extra_id_12>",
203
+ "<extra_id_13>",
204
+ "<extra_id_14>",
205
+ "<extra_id_15>",
206
+ "<extra_id_16>",
207
+ "<extra_id_17>",
208
+ "<extra_id_18>",
209
+ "<extra_id_19>"
210
+ ],
211
+ "clean_up_tokenization_spaces": true,
212
+ "eos_token": "</s>",
213
+ "extra_ids": 20,
214
+ "legacy": true,
215
+ "model_max_length": 1000000000000000019884624838656,
216
+ "pad_token": "<pad>",
217
+ "sp_model_kwargs": {},
218
+ "tokenizer_class": "T5Tokenizer",
219
+ "unk_token": "<unk>"
220
+ }