Hugging Face's logo

mrpintime
/
GPTPoem

Text Generation
Transformers
Safetensors
English
gpt2
text-generation-inference
Model card Files
xet
 Community
mrpintime commited on
Commit
532cef7
·
verified ·
1 Parent(s): fc2d4ef

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +6 -38
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +11 -250
special_tokens_map.json CHANGED
@@ -1,42 +1,10 @@
1
  {
2
- "additional_special_tokens": [
3
- "[EOD]",
4
- "[CLS]",
5
- "[PAD]",
6
- "[BOM]",
7
- "[BOS]",
8
- "[EOS]",
9
- "[BOP]",
10
- "[EOP]",
11
- "[LAT]",
12
- "[URL]",
13
- "[KRK]",
14
- "[NUM]",
15
- "[UNK]",
16
- "۰",
17
- "۱",
18
- "۲",
19
- "۳",
20
- "۴",
21
- "۵",
22
- "۶",
23
- "۷",
24
- "۸",
25
- "۹",
26
- "[MSK]",
27
- "[EOL]"
28
- ],
29
  "bos_token": "[BOS]",
30
- "cls_token": "[CLS]",
31
  "eos_token": "[EOS]",
32
- "mask_token": {
33
- "content": "[MSK]",
34
- "lstrip": true,
35
- "normalized": false,
36
- "rstrip": false,
37
- "single_word": false
38
- },
39
- "pad_token": "[PAD]",
40
  "sep_token": "[SEP]",
41
- "unk_token": "[UNK]"
42
- }
 
 
 
 
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "bos_token": "[BOS]",
 
3
  "eos_token": "[EOS]",
4
+ "unk_token": "[UNK]",
 
 
 
 
 
 
 
5
  "sep_token": "[SEP]",
6
+ "pad_token": "[PAD]",
7
+ "cls_token": "[CLS]",
8
+ "mask_token": "[MSK]",
9
+ "additional_special_tokens": ["[EOD]", "[CLS]", "[PAD]", "[BOM]", "[BOS]", "[EOS]", "[BOP]", "[EOP]", "[LAT]", "[URL]", "[KRK]", "[NUM]", "[UNK]", "۰", "۱", "۲", "۳", "۴", "۵", "۶", "۷", "۸", "۹", "[MSK]", "[EOL]"]
10
+ }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,256 +1,17 @@
1
  {
2
- "added_tokens_decoder": {
3
- "3": {
4
- "content": "[SEP]",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "4": {
12
- "content": "[EOD]",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "5": {
20
- "content": "[CLS]",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "6": {
28
- "content": "[PAD]",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "7": {
36
- "content": "[BOM]",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- },
43
- "8": {
44
- "content": "[BOS]",
45
- "lstrip": false,
46
- "normalized": false,
47
- "rstrip": false,
48
- "single_word": false,
49
- "special": true
50
- },
51
- "9": {
52
- "content": "[EOS]",
53
- "lstrip": false,
54
- "normalized": false,
55
- "rstrip": false,
56
- "single_word": false,
57
- "special": true
58
- },
59
- "10": {
60
- "content": "[BOP]",
61
- "lstrip": false,
62
- "normalized": false,
63
- "rstrip": false,
64
- "single_word": false,
65
- "special": true
66
- },
67
- "11": {
68
- "content": "[EOP]",
69
- "lstrip": false,
70
- "normalized": false,
71
- "rstrip": false,
72
- "single_word": false,
73
- "special": true
74
- },
75
- "12": {
76
- "content": "[LAT]",
77
- "lstrip": false,
78
- "normalized": false,
79
- "rstrip": false,
80
- "single_word": false,
81
- "special": true
82
- },
83
- "13": {
84
- "content": "[URL]",
85
- "lstrip": false,
86
- "normalized": false,
87
- "rstrip": false,
88
- "single_word": false,
89
- "special": true
90
- },
91
- "14": {
92
- "content": "[KRK]",
93
- "lstrip": false,
94
- "normalized": false,
95
- "rstrip": false,
96
- "single_word": false,
97
- "special": true
98
- },
99
- "15": {
100
- "content": "[NUM]",
101
- "lstrip": false,
102
- "normalized": false,
103
- "rstrip": false,
104
- "single_word": false,
105
- "special": true
106
- },
107
- "16": {
108
- "content": "[UNK]",
109
- "lstrip": false,
110
- "normalized": false,
111
- "rstrip": false,
112
- "single_word": false,
113
- "special": true
114
- },
115
- "17": {
116
- "content": "۰",
117
- "lstrip": false,
118
- "normalized": false,
119
- "rstrip": false,
120
- "single_word": false,
121
- "special": true
122
- },
123
- "18": {
124
- "content": "۱",
125
- "lstrip": false,
126
- "normalized": false,
127
- "rstrip": false,
128
- "single_word": false,
129
- "special": true
130
- },
131
- "19": {
132
- "content": "۲",
133
- "lstrip": false,
134
- "normalized": false,
135
- "rstrip": false,
136
- "single_word": false,
137
- "special": true
138
- },
139
- "20": {
140
- "content": "۳",
141
- "lstrip": false,
142
- "normalized": false,
143
- "rstrip": false,
144
- "single_word": false,
145
- "special": true
146
- },
147
- "21": {
148
- "content": "۴",
149
- "lstrip": false,
150
- "normalized": false,
151
- "rstrip": false,
152
- "single_word": false,
153
- "special": true
154
- },
155
- "22": {
156
- "content": "۵",
157
- "lstrip": false,
158
- "normalized": false,
159
- "rstrip": false,
160
- "single_word": false,
161
- "special": true
162
- },
163
- "23": {
164
- "content": "۶",
165
- "lstrip": false,
166
- "normalized": false,
167
- "rstrip": false,
168
- "single_word": false,
169
- "special": true
170
- },
171
- "24": {
172
- "content": "۷",
173
- "lstrip": false,
174
- "normalized": false,
175
- "rstrip": false,
176
- "single_word": false,
177
- "special": true
178
- },
179
- "25": {
180
- "content": "۸",
181
- "lstrip": false,
182
- "normalized": false,
183
- "rstrip": false,
184
- "single_word": false,
185
- "special": true
186
- },
187
- "26": {
188
- "content": "۹",
189
- "lstrip": false,
190
- "normalized": false,
191
- "rstrip": false,
192
- "single_word": false,
193
- "special": true
194
- },
195
- "28": {
196
- "content": "[EOL]",
197
- "lstrip": false,
198
- "normalized": false,
199
- "rstrip": false,
200
- "single_word": false,
201
- "special": true
202
- },
203
- "25000": {
204
- "content": "[MSK]",
205
- "lstrip": true,
206
- "normalized": false,
207
- "rstrip": false,
208
- "single_word": false,
209
- "special": true
210
- }
211
- },
212
- "additional_special_tokens": [
213
- "[EOD]",
214
- "[CLS]",
215
- "[PAD]",
216
- "[BOM]",
217
- "[BOS]",
218
- "[EOS]",
219
- "[BOP]",
220
- "[EOP]",
221
- "[LAT]",
222
- "[URL]",
223
- "[KRK]",
224
- "[NUM]",
225
- "[UNK]",
226
- "۰",
227
- "۱",
228
- "۲",
229
- "۳",
230
- "۴",
231
- "۵",
232
- "۶",
233
- "۷",
234
- "۸",
235
- "۹",
236
- "[MSK]",
237
- "[EOL]"
238
- ],
239
- "bos_token": "[BOS]",
240
- "clean_up_tokenization_spaces": true,
241
- "cls_token": "[CLS]",
242
  "do_lower_case": false,
243
- "eos_token": "[EOS]",
244
  "keep_accents": true,
 
 
 
 
 
 
245
  "mask_token": "[MSK]",
246
- "model_max_length": 1000000000000000019884624838656,
247
  "normalizer": {
248
- "normalizers": [],
249
- "type": "Sequence"
250
  },
251
- "pad_token": "[PAD]",
252
- "remove_space": true,
253
- "sep_token": "[SEP]",
254
- "tokenizer_class": "AlbertTokenizer",
255
- "unk_token": "[UNK]"
256
- }
 
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "do_lower_case": false,
3
+ "remove_space": true,
4
  "keep_accents": true,
5
+ "bos_token": "[BOS]",
6
+ "eos_token": "[EOS]",
7
+ "unk_token": "[UNK]",
8
+ "sep_token": "[SEP]",
9
+ "pad_token": "[PAD]",
10
+ "cls_token": "[CLS]",
11
  "mask_token": "[MSK]",
 
12
  "normalizer": {
13
+ "type": "Sequence",
14
+ "normalizers": []
15
  },
16
+ "name_or_path": "./spiece.model"
17
+ }