Hugging Face's logo

Samuael
/
amBART-big

Transformers
Model card Files
xet
 Community
Samuael commited on
Commit
ca56b17
·
verified ·
1 Parent(s): 85c4a08

Update tokenizer_config.json

Browse files

Added to additional tokens for am_CR and am_IC

Files changed (1) hide show
  1. tokenizer_config.json +6 -213
tokenizer_config.json CHANGED
@@ -33,7 +33,7 @@
33
  "special": true
34
  },
35
  "20001": {
36
- "content": "ar_AR",
37
  "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
@@ -41,191 +41,7 @@
41
  "special": true
42
  },
43
  "20002": {
44
- "content": "cs_CZ",
45
- "lstrip": false,
46
- "normalized": false,
47
- "rstrip": false,
48
- "single_word": false,
49
- "special": true
50
- },
51
- "20003": {
52
- "content": "de_DE",
53
- "lstrip": false,
54
- "normalized": false,
55
- "rstrip": false,
56
- "single_word": false,
57
- "special": true
58
- },
59
- "20004": {
60
- "content": "en_XX",
61
- "lstrip": false,
62
- "normalized": false,
63
- "rstrip": false,
64
- "single_word": false,
65
- "special": true
66
- },
67
- "20005": {
68
- "content": "es_XX",
69
- "lstrip": false,
70
- "normalized": false,
71
- "rstrip": false,
72
- "single_word": false,
73
- "special": true
74
- },
75
- "20006": {
76
- "content": "et_EE",
77
- "lstrip": false,
78
- "normalized": false,
79
- "rstrip": false,
80
- "single_word": false,
81
- "special": true
82
- },
83
- "20007": {
84
- "content": "fi_FI",
85
- "lstrip": false,
86
- "normalized": false,
87
- "rstrip": false,
88
- "single_word": false,
89
- "special": true
90
- },
91
- "20008": {
92
- "content": "fr_XX",
93
- "lstrip": false,
94
- "normalized": false,
95
- "rstrip": false,
96
- "single_word": false,
97
- "special": true
98
- },
99
- "20009": {
100
- "content": "gu_IN",
101
- "lstrip": false,
102
- "normalized": false,
103
- "rstrip": false,
104
- "single_word": false,
105
- "special": true
106
- },
107
- "20010": {
108
- "content": "hi_IN",
109
- "lstrip": false,
110
- "normalized": false,
111
- "rstrip": false,
112
- "single_word": false,
113
- "special": true
114
- },
115
- "20011": {
116
- "content": "it_IT",
117
- "lstrip": false,
118
- "normalized": false,
119
- "rstrip": false,
120
- "single_word": false,
121
- "special": true
122
- },
123
- "20012": {
124
- "content": "ja_XX",
125
- "lstrip": false,
126
- "normalized": false,
127
- "rstrip": false,
128
- "single_word": false,
129
- "special": true
130
- },
131
- "20013": {
132
- "content": "kk_KZ",
133
- "lstrip": false,
134
- "normalized": false,
135
- "rstrip": false,
136
- "single_word": false,
137
- "special": true
138
- },
139
- "20014": {
140
- "content": "ko_KR",
141
- "lstrip": false,
142
- "normalized": false,
143
- "rstrip": false,
144
- "single_word": false,
145
- "special": true
146
- },
147
- "20015": {
148
- "content": "lt_LT",
149
- "lstrip": false,
150
- "normalized": false,
151
- "rstrip": false,
152
- "single_word": false,
153
- "special": true
154
- },
155
- "20016": {
156
- "content": "lv_LV",
157
- "lstrip": false,
158
- "normalized": false,
159
- "rstrip": false,
160
- "single_word": false,
161
- "special": true
162
- },
163
- "20017": {
164
- "content": "my_MM",
165
- "lstrip": false,
166
- "normalized": false,
167
- "rstrip": false,
168
- "single_word": false,
169
- "special": true
170
- },
171
- "20018": {
172
- "content": "ne_NP",
173
- "lstrip": false,
174
- "normalized": false,
175
- "rstrip": false,
176
- "single_word": false,
177
- "special": true
178
- },
179
- "20019": {
180
- "content": "nl_XX",
181
- "lstrip": false,
182
- "normalized": false,
183
- "rstrip": false,
184
- "single_word": false,
185
- "special": true
186
- },
187
- "20020": {
188
- "content": "ro_RO",
189
- "lstrip": false,
190
- "normalized": false,
191
- "rstrip": false,
192
- "single_word": false,
193
- "special": true
194
- },
195
- "20021": {
196
- "content": "ru_RU",
197
- "lstrip": false,
198
- "normalized": false,
199
- "rstrip": false,
200
- "single_word": false,
201
- "special": true
202
- },
203
- "20022": {
204
- "content": "si_LK",
205
- "lstrip": false,
206
- "normalized": false,
207
- "rstrip": false,
208
- "single_word": false,
209
- "special": true
210
- },
211
- "20023": {
212
- "content": "tr_TR",
213
- "lstrip": false,
214
- "normalized": false,
215
- "rstrip": false,
216
- "single_word": false,
217
- "special": true
218
- },
219
- "20024": {
220
- "content": "vi_VN",
221
- "lstrip": false,
222
- "normalized": false,
223
- "rstrip": false,
224
- "single_word": false,
225
- "special": true
226
- },
227
- "20025": {
228
- "content": "zh_CN",
229
  "lstrip": false,
230
  "normalized": false,
231
  "rstrip": false,
@@ -234,31 +50,8 @@
234
  }
235
  },
236
  "additional_special_tokens": [
237
- "ar_AR",
238
- "cs_CZ",
239
- "de_DE",
240
- "en_XX",
241
- "es_XX",
242
- "et_EE",
243
- "fi_FI",
244
- "fr_XX",
245
- "gu_IN",
246
- "hi_IN",
247
- "it_IT",
248
- "ja_XX",
249
- "kk_KZ",
250
- "ko_KR",
251
- "lt_LT",
252
- "lv_LV",
253
- "my_MM",
254
- "ne_NP",
255
- "nl_XX",
256
- "ro_RO",
257
- "ru_RU",
258
- "si_LK",
259
- "tr_TR",
260
- "vi_VN",
261
- "zh_CN"
262
  ],
263
  "bos_token": "<s>",
264
  "clean_up_tokenization_spaces": true,
@@ -269,8 +62,8 @@
269
  "pad_token": "<pad>",
270
  "sep_token": "</s>",
271
  "sp_model_kwargs": {},
272
- "src_lang": "en_XX",
273
- "tgt_lang": null,
274
  "tokenizer_class": "MBartTokenizer",
275
  "tokenizer_file": null,
276
  "unk_token": "<unk>"
 
33
  "special": true
34
  },
35
  "20001": {
36
+ "content": "am_CR",
37
  "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
 
41
  "special": true
42
  },
43
  "20002": {
44
+ "content": "am_IC",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45
  "lstrip": false,
46
  "normalized": false,
47
  "rstrip": false,
 
50
  }
51
  },
52
  "additional_special_tokens": [
53
+ "am_CR",
54
+ "am_IC"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  ],
56
  "bos_token": "<s>",
57
  "clean_up_tokenization_spaces": true,
 
62
  "pad_token": "<pad>",
63
  "sep_token": "</s>",
64
  "sp_model_kwargs": {},
65
+ "src_lang": "am_IC",
66
+ "tgt_lang": "am_CR",
67
  "tokenizer_class": "MBartTokenizer",
68
  "tokenizer_file": null,
69
  "unk_token": "<unk>"