Hugging Face's logo

Tofa08
/
Sarcasm_Model

TensorFlow
Safetensors
English
roberta
Model card Files
xet
Community
Tofa08 commited on
Commit
bf6ecb5
·
verified ·
1 Parent(s): 9f3eebd

Upload tokenizer

Browse files
Files changed (4) hide show
  1. README.md +1 -2
  2. special_tokens_map.json +6 -20
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +206 -19
README.md CHANGED
@@ -1,8 +1,7 @@
1
-
2
  ---
3
- license: apache-2.0
4
  language:
5
  - en
 
6
  metrics:
7
  - accuracy
8
  - f1
 
 
1
  ---
 
2
  language:
3
  - en
4
+ license: apache-2.0
5
  metrics:
6
  - accuracy
7
  - f1
special_tokens_map.json CHANGED
@@ -1,48 +1,34 @@
1
  {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
  "cls_token": {
10
- "content": "<s>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "eos_token": {
17
- "content": "</s>",
18
  "lstrip": false,
19
  "normalized": false,
20
  "rstrip": false,
21
  "single_word": false
22
  },
23
  "mask_token": {
24
- "content": "<mask>",
25
- "lstrip": true,
26
  "normalized": false,
27
  "rstrip": false,
28
  "single_word": false
29
  },
30
  "pad_token": {
31
- "content": "<pad>",
32
  "lstrip": false,
33
  "normalized": false,
34
  "rstrip": false,
35
  "single_word": false
36
  },
37
  "sep_token": {
38
- "content": "</s>",
39
  "lstrip": false,
40
  "normalized": false,
41
  "rstrip": false,
42
  "single_word": false
43
  },
44
  "unk_token": {
45
- "content": "<unk>",
46
  "lstrip": false,
47
  "normalized": false,
48
  "rstrip": false,
 
1
  {
 
 
 
 
 
 
 
2
  "cls_token": {
3
+ "content": "[CLS]",
 
 
 
 
 
 
 
4
  "lstrip": false,
5
  "normalized": false,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
  "pad_token": {
17
+ "content": "[PAD]",
18
  "lstrip": false,
19
  "normalized": false,
20
  "rstrip": false,
21
  "single_word": false
22
  },
23
  "sep_token": {
24
+ "content": "[SEP]",
25
  "lstrip": false,
26
  "normalized": false,
27
  "rstrip": false,
28
  "single_word": false
29
  },
30
  "unk_token": {
31
+ "content": "[UNK]",
32
  "lstrip": false,
33
  "normalized": false,
34
  "rstrip": false,
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,8 +1,7 @@
1
  {
2
- "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
  "0": {
5
- "content": "<s>",
6
  "lstrip": false,
7
  "normalized": false,
8
  "rstrip": false,
@@ -10,7 +9,7 @@
10
  "special": true
11
  },
12
  "1": {
13
- "content": "<pad>",
14
  "lstrip": false,
15
  "normalized": false,
16
  "rstrip": false,
@@ -18,7 +17,7 @@
18
  "special": true
19
  },
20
  "2": {
21
- "content": "</s>",
22
  "lstrip": false,
23
  "normalized": false,
24
  "rstrip": false,
@@ -26,32 +25,220 @@
26
  "special": true
27
  },
28
  "3": {
29
- "content": "<unk>",
30
  "lstrip": false,
31
  "normalized": false,
32
  "rstrip": false,
33
  "single_word": false,
34
  "special": true
35
  },
36
- "50264": {
37
- "content": "<mask>",
38
- "lstrip": true,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39
  "normalized": false,
40
  "rstrip": false,
41
  "single_word": false,
42
  "special": true
43
  }
44
  },
45
- "bos_token": "<s>",
46
  "clean_up_tokenization_spaces": true,
47
- "cls_token": "<s>",
48
- "eos_token": "</s>",
49
- "errors": "replace",
50
- "mask_token": "<mask>",
51
- "model_max_length": 512,
52
- "pad_token": "<pad>",
53
- "sep_token": "</s>",
54
- "tokenizer_class": "RobertaTokenizer",
55
- "trim_offsets": true,
56
- "unk_token": "<unk>"
57
  }
 
1
  {
 
2
  "added_tokens_decoder": {
3
  "0": {
4
+ "content": "[UNK]",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
 
9
  "special": true
10
  },
11
  "1": {
12
+ "content": "[CLS]",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
 
17
  "special": true
18
  },
19
  "2": {
20
+ "content": "[SEP]",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
 
25
  "special": true
26
  },
27
  "3": {
28
+ "content": "[PAD]",
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
+ "5": {
44
+ "content": "<as>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "<bd>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "<bn>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "8": {
68
+ "content": "<dg>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "9": {
76
+ "content": "<en>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "10": {
84
+ "content": "<gom>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "11": {
92
+ "content": "<gu>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "12": {
100
+ "content": "<hi>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "13": {
108
+ "content": "<kha>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "14": {
116
+ "content": "<kn>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "15": {
124
+ "content": "<ks>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "16": {
132
+ "content": "<mai>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "17": {
140
+ "content": "<ml>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "18": {
148
+ "content": "<mni>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "19": {
156
+ "content": "<mr>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "20": {
164
+ "content": "<ne>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "21": {
172
+ "content": "<or>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "22": {
180
+ "content": "<pa>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "23": {
188
+ "content": "<sa>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "24": {
196
+ "content": "<sd>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "25": {
204
+ "content": "<sat>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "26": {
212
+ "content": "<ta>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "27": {
220
+ "content": "<te>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "28": {
228
+ "content": "<ur>",
229
+ "lstrip": false,
230
  "normalized": false,
231
  "rstrip": false,
232
  "single_word": false,
233
  "special": true
234
  }
235
  },
 
236
  "clean_up_tokenization_spaces": true,
237
+ "cls_token": "[CLS]",
238
+ "mask_token": "[MASK]",
239
+ "model_max_length": 1000000000000000019884624838656,
240
+ "pad_token": "[PAD]",
241
+ "sep_token": "[SEP]",
242
+ "tokenizer_class": "PreTrainedTokenizerFast",
243
+ "unk_token": "[UNK]"
 
 
 
244
  }