Hugging Face's logo

irp1999
/
mbart-neutralization

Text2Text Generation
Transformers
TensorBoard
Safetensors
mbart
simplification
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
irp1999 commited on
Commit
b572f6b
•
1 Parent(s): e15341f

Training complete

Browse files
Files changed (8) hide show
  1. README.md +12 -12
  2. config.json +48 -52
  3. generation_config.json +8 -3
  4. model.safetensors +2 -2
  5. special_tokens_map.json +62 -118
  6. tokenizer.json +2 -2
  7. tokenizer_config.json +173 -584
  8. training_args.bin +1 -1
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
- license: apache-2.0
3
- base_model: google/flan-t5-base
4
  tags:
5
  - simplification
6
  - generated_from_trainer
@@ -16,11 +16,11 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # mbart-neutralization
18
 
19
- This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 1.3981
22
- - Bleu: 0.8291
23
- - Gen Len: 19.0
24
 
25
  ## Model description
26
 
@@ -40,8 +40,8 @@ More information needed
40
 
41
  The following hyperparameters were used during training:
42
  - learning_rate: 5.6e-05
43
- - train_batch_size: 1
44
- - eval_batch_size: 1
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
@@ -49,10 +49,10 @@ The following hyperparameters were used during training:
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
53
- |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
54
- | No log | 1.0 | 121 | 1.4544 | 0.9156 | 19.0 |
55
- | No log | 2.0 | 242 | 1.3981 | 0.8291 | 19.0 |
56
 
57
 
58
  ### Framework versions
 
1
  ---
2
+ license: mit
3
+ base_model: facebook/mbart-large-50
4
  tags:
5
  - simplification
6
  - generated_from_trainer
 
16
 
17
  # mbart-neutralization
18
 
19
+ This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.0181
22
+ - Bleu: 98.7341
23
+ - Gen Len: 18.4896
24
 
25
  ## Model description
26
 
 
40
 
41
  The following hyperparameters were used during training:
42
  - learning_rate: 5.6e-05
43
+ - train_batch_size: 8
44
+ - eval_batch_size: 8
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
 
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
53
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
54
+ | No log | 1.0 | 440 | 0.0307 | 91.2911 | 18.25 |
55
+ | 0.2343 | 2.0 | 880 | 0.0181 | 98.7341 | 18.4896 |
56
 
57
 
58
  ### Framework versions
config.json CHANGED
@@ -1,62 +1,58 @@
1
  {
2
- "_name_or_path": "google/flan-t5-base",
 
 
 
 
 
3
  "architectures": [
4
- "T5ForConditionalGeneration"
5
  ],
 
 
 
6
  "classifier_dropout": 0.0,
7
- "d_ff": 2048,
8
- "d_kv": 64,
9
- "d_model": 768,
10
- "decoder_start_token_id": 0,
11
- "dense_act_fn": "gelu_new",
12
- "dropout_rate": 0.1,
13
- "eos_token_id": 1,
14
- "feed_forward_proj": "gated-gelu",
15
- "initializer_factor": 1.0,
 
 
 
 
 
 
 
 
 
 
 
 
16
  "is_encoder_decoder": true,
17
- "is_gated_act": true,
18
- "layer_norm_epsilon": 1e-06,
19
- "model_type": "t5",
20
- "n_positions": 512,
21
- "num_decoder_layers": 12,
22
- "num_heads": 12,
23
- "num_layers": 12,
24
- "output_past": true,
25
- "pad_token_id": 0,
26
- "relative_attention_max_distance": 128,
27
- "relative_attention_num_buckets": 32,
28
- "task_specific_params": {
29
- "summarization": {
30
- "early_stopping": true,
31
- "length_penalty": 2.0,
32
- "max_length": 200,
33
- "min_length": 30,
34
- "no_repeat_ngram_size": 3,
35
- "num_beams": 4,
36
- "prefix": "summarize: "
37
- },
38
- "translation_en_to_de": {
39
- "early_stopping": true,
40
- "max_length": 300,
41
- "num_beams": 4,
42
- "prefix": "translate English to German: "
43
- },
44
- "translation_en_to_fr": {
45
- "early_stopping": true,
46
- "max_length": 300,
47
- "num_beams": 4,
48
- "prefix": "translate English to French: "
49
- },
50
- "translation_en_to_ro": {
51
- "early_stopping": true,
52
- "max_length": 300,
53
- "num_beams": 4,
54
- "prefix": "translate English to Romanian: "
55
- }
56
  },
57
- "tie_word_embeddings": false,
 
 
 
 
 
 
 
 
 
 
 
58
  "torch_dtype": "float32",
59
  "transformers_version": "4.37.2",
60
  "use_cache": true,
61
- "vocab_size": 32128
62
  }
 
1
  {
2
+ "_name_or_path": "facebook/mbart-large-50",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "gelu",
6
+ "add_bias_logits": false,
7
+ "add_final_layer_norm": true,
8
  "architectures": [
9
+ "MBartForConditionalGeneration"
10
  ],
11
+ "attention_dropout": 0.0,
12
+ "bos_token_id": 0,
13
+ "classif_dropout": 0.0,
14
  "classifier_dropout": 0.0,
15
+ "d_model": 1024,
16
+ "decoder_attention_heads": 16,
17
+ "decoder_ffn_dim": 4096,
18
+ "decoder_layerdrop": 0.0,
19
+ "decoder_layers": 12,
20
+ "decoder_start_token_id": 2,
21
+ "dropout": 0.1,
22
+ "early_stopping": true,
23
+ "encoder_attention_heads": 16,
24
+ "encoder_ffn_dim": 4096,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 12,
27
+ "eos_token_id": 2,
28
+ "forced_eos_token_id": 2,
29
+ "gradient_checkpointing": false,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1",
33
+ "2": "LABEL_2"
34
+ },
35
+ "init_std": 0.02,
36
  "is_encoder_decoder": true,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1,
40
+ "LABEL_2": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
41
  },
42
+ "max_length": 200,
43
+ "max_position_embeddings": 1024,
44
+ "model_type": "mbart",
45
+ "normalize_before": true,
46
+ "normalize_embedding": true,
47
+ "num_beams": 5,
48
+ "num_hidden_layers": 12,
49
+ "output_past": true,
50
+ "pad_token_id": 1,
51
+ "scale_embedding": true,
52
+ "static_position_embeddings": false,
53
+ "tokenizer_class": "MBart50Tokenizer",
54
  "torch_dtype": "float32",
55
  "transformers_version": "4.37.2",
56
  "use_cache": true,
57
+ "vocab_size": 250054
58
  }
generation_config.json CHANGED
@@ -1,6 +1,11 @@
1
  {
2
- "decoder_start_token_id": 0,
3
- "eos_token_id": 1,
4
- "pad_token_id": 0,
 
 
 
 
 
5
  "transformers_version": "4.37.2"
6
  }
 
1
  {
2
+ "bos_token_id": 0,
3
+ "decoder_start_token_id": 2,
4
+ "early_stopping": true,
5
+ "eos_token_id": 2,
6
+ "forced_eos_token_id": 2,
7
+ "max_length": 200,
8
+ "num_beams": 5,
9
+ "pad_token_id": 1,
10
  "transformers_version": "4.37.2"
11
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33d0e82b4f03f384aed1b7f34d57559ccd39d8be7d75474cfa91c4d555fa2844
3
- size 990345064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be81fdab8cada8f8cdd8d57dfd898b9eeb36743291ee9865ff988dadb47b2efc
3
+ size 2444578688
special_tokens_map.json CHANGED
@@ -1,125 +1,69 @@
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
- "<extra_id_20>",
24
- "<extra_id_21>",
25
- "<extra_id_22>",
26
- "<extra_id_23>",
27
- "<extra_id_24>",
28
- "<extra_id_25>",
29
- "<extra_id_26>",
30
- "<extra_id_27>",
31
- "<extra_id_28>",
32
- "<extra_id_29>",
33
- "<extra_id_30>",
34
- "<extra_id_31>",
35
- "<extra_id_32>",
36
- "<extra_id_33>",
37
- "<extra_id_34>",
38
- "<extra_id_35>",
39
- "<extra_id_36>",
40
- "<extra_id_37>",
41
- "<extra_id_38>",
42
- "<extra_id_39>",
43
- "<extra_id_40>",
44
- "<extra_id_41>",
45
- "<extra_id_42>",
46
- "<extra_id_43>",
47
- "<extra_id_44>",
48
- "<extra_id_45>",
49
- "<extra_id_46>",
50
- "<extra_id_47>",
51
- "<extra_id_48>",
52
- "<extra_id_49>",
53
- "<extra_id_50>",
54
- "<extra_id_51>",
55
- "<extra_id_52>",
56
- "<extra_id_53>",
57
- "<extra_id_54>",
58
- "<extra_id_55>",
59
- "<extra_id_56>",
60
- "<extra_id_57>",
61
- "<extra_id_58>",
62
- "<extra_id_59>",
63
- "<extra_id_60>",
64
- "<extra_id_61>",
65
- "<extra_id_62>",
66
- "<extra_id_63>",
67
- "<extra_id_64>",
68
- "<extra_id_65>",
69
- "<extra_id_66>",
70
- "<extra_id_67>",
71
- "<extra_id_68>",
72
- "<extra_id_69>",
73
- "<extra_id_70>",
74
- "<extra_id_71>",
75
- "<extra_id_72>",
76
- "<extra_id_73>",
77
- "<extra_id_74>",
78
- "<extra_id_75>",
79
- "<extra_id_76>",
80
- "<extra_id_77>",
81
- "<extra_id_78>",
82
- "<extra_id_79>",
83
- "<extra_id_80>",
84
- "<extra_id_81>",
85
- "<extra_id_82>",
86
- "<extra_id_83>",
87
- "<extra_id_84>",
88
- "<extra_id_85>",
89
- "<extra_id_86>",
90
- "<extra_id_87>",
91
- "<extra_id_88>",
92
- "<extra_id_89>",
93
- "<extra_id_90>",
94
- "<extra_id_91>",
95
- "<extra_id_92>",
96
- "<extra_id_93>",
97
- "<extra_id_94>",
98
- "<extra_id_95>",
99
- "<extra_id_96>",
100
- "<extra_id_97>",
101
- "<extra_id_98>",
102
- "<extra_id_99>"
103
  ],
104
- "eos_token": {
105
- "content": "</s>",
106
- "lstrip": false,
107
- "normalized": false,
 
 
 
108
  "rstrip": false,
109
  "single_word": false
110
  },
111
- "pad_token": {
112
- "content": "<pad>",
113
- "lstrip": false,
114
- "normalized": false,
115
- "rstrip": false,
116
- "single_word": false
117
- },
118
- "unk_token": {
119
- "content": "<unk>",
120
- "lstrip": false,
121
- "normalized": false,
122
- "rstrip": false,
123
- "single_word": false
124
- }
125
  }
 
1
  {
2
  "additional_special_tokens": [
3
+ "ar_AR",
4
+ "cs_CZ",
5
+ "de_DE",
6
+ "en_XX",
7
+ "es_XX",
8
+ "et_EE",
9
+ "fi_FI",
10
+ "fr_XX",
11
+ "gu_IN",
12
+ "hi_IN",
13
+ "it_IT",
14
+ "ja_XX",
15
+ "kk_KZ",
16
+ "ko_KR",
17
+ "lt_LT",
18
+ "lv_LV",
19
+ "my_MM",
20
+ "ne_NP",
21
+ "nl_XX",
22
+ "ro_RO",
23
+ "ru_RU",
24
+ "si_LK",
25
+ "tr_TR",
26
+ "vi_VN",
27
+ "zh_CN",
28
+ "af_ZA",
29
+ "az_AZ",
30
+ "bn_IN",
31
+ "fa_IR",
32
+ "he_IL",
33
+ "hr_HR",
34
+ "id_ID",
35
+ "ka_GE",
36
+ "km_KH",
37
+ "mk_MK",
38
+ "ml_IN",
39
+ "mn_MN",
40
+ "mr_IN",
41
+ "pl_PL",
42
+ "ps_AF",
43
+ "pt_XX",
44
+ "sv_SE",
45
+ "sw_KE",
46
+ "ta_IN",
47
+ "te_IN",
48
+ "th_TH",
49
+ "tl_XX",
50
+ "uk_UA",
51
+ "ur_PK",
52
+ "xh_ZA",
53
+ "gl_ES",
54
+ "sl_SI"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  ],
56
+ "bos_token": "<s>",
57
+ "cls_token": "<s>",
58
+ "eos_token": "</s>",
59
+ "mask_token": {
60
+ "content": "<mask>",
61
+ "lstrip": true,
62
+ "normalized": true,
63
  "rstrip": false,
64
  "single_word": false
65
  },
66
+ "pad_token": "<pad>",
67
+ "sep_token": "</s>",
68
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
69
  }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5009c0a1e18735c5d7823cbc89bd3e7467ab739f611cd58901f0d06a0ba90f9e
3
- size 2422354
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9472a5f3613a4d5b4fc0bc78c944dd2edbcb2ceed3defe1c760efdc0ffc0fded
3
+ size 17110041
tokenizer_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
- "content": "<pad>",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
@@ -9,7 +9,7 @@
9
  "special": true
10
  },
11
  "1": {
12
- "content": "</s>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
@@ -17,922 +17,511 @@
17
  "special": true
18
  },
19
  "2": {
20
- "content": "<unk>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "32000": {
28
- "content": "<extra_id_99>",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "32001": {
36
- "content": "<extra_id_98>",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- },
43
- "32002": {
44
- "content": "<extra_id_97>",
45
- "lstrip": false,
46
- "normalized": false,
47
- "rstrip": false,
48
- "single_word": false,
49
- "special": true
50
- },
51
- "32003": {
52
- "content": "<extra_id_96>",
53
- "lstrip": false,
54
- "normalized": false,
55
- "rstrip": false,
56
- "single_word": false,
57
- "special": true
58
- },
59
- "32004": {
60
- "content": "<extra_id_95>",
61
- "lstrip": false,
62
- "normalized": false,
63
- "rstrip": false,
64
- "single_word": false,
65
- "special": true
66
- },
67
- "32005": {
68
- "content": "<extra_id_94>",
69
- "lstrip": false,
70
- "normalized": false,
71
- "rstrip": false,
72
- "single_word": false,
73
- "special": true
74
- },
75
- "32006": {
76
- "content": "<extra_id_93>",
77
- "lstrip": false,
78
- "normalized": false,
79
- "rstrip": false,
80
- "single_word": false,
81
- "special": true
82
- },
83
- "32007": {
84
- "content": "<extra_id_92>",
85
- "lstrip": false,
86
- "normalized": false,
87
- "rstrip": false,
88
- "single_word": false,
89
- "special": true
90
- },
91
- "32008": {
92
- "content": "<extra_id_91>",
93
- "lstrip": false,
94
- "normalized": false,
95
- "rstrip": false,
96
- "single_word": false,
97
- "special": true
98
- },
99
- "32009": {
100
- "content": "<extra_id_90>",
101
- "lstrip": false,
102
- "normalized": false,
103
- "rstrip": false,
104
- "single_word": false,
105
- "special": true
106
- },
107
- "32010": {
108
- "content": "<extra_id_89>",
109
- "lstrip": false,
110
- "normalized": false,
111
- "rstrip": false,
112
- "single_word": false,
113
- "special": true
114
- },
115
- "32011": {
116
- "content": "<extra_id_88>",
117
- "lstrip": false,
118
- "normalized": false,
119
- "rstrip": false,
120
- "single_word": false,
121
- "special": true
122
- },
123
- "32012": {
124
- "content": "<extra_id_87>",
125
- "lstrip": false,
126
- "normalized": false,
127
- "rstrip": false,
128
- "single_word": false,
129
- "special": true
130
- },
131
- "32013": {
132
- "content": "<extra_id_86>",
133
- "lstrip": false,
134
- "normalized": false,
135
- "rstrip": false,
136
- "single_word": false,
137
- "special": true
138
- },
139
- "32014": {
140
- "content": "<extra_id_85>",
141
- "lstrip": false,
142
- "normalized": false,
143
- "rstrip": false,
144
- "single_word": false,
145
- "special": true
146
- },
147
- "32015": {
148
- "content": "<extra_id_84>",
149
- "lstrip": false,
150
- "normalized": false,
151
- "rstrip": false,
152
- "single_word": false,
153
- "special": true
154
- },
155
- "32016": {
156
- "content": "<extra_id_83>",
157
- "lstrip": false,
158
- "normalized": false,
159
- "rstrip": false,
160
- "single_word": false,
161
- "special": true
162
- },
163
- "32017": {
164
- "content": "<extra_id_82>",
165
- "lstrip": false,
166
- "normalized": false,
167
- "rstrip": false,
168
- "single_word": false,
169
- "special": true
170
- },
171
- "32018": {
172
- "content": "<extra_id_81>",
173
- "lstrip": false,
174
- "normalized": false,
175
- "rstrip": false,
176
- "single_word": false,
177
- "special": true
178
- },
179
- "32019": {
180
- "content": "<extra_id_80>",
181
- "lstrip": false,
182
- "normalized": false,
183
- "rstrip": false,
184
- "single_word": false,
185
- "special": true
186
- },
187
- "32020": {
188
- "content": "<extra_id_79>",
189
- "lstrip": false,
190
- "normalized": false,
191
- "rstrip": false,
192
- "single_word": false,
193
- "special": true
194
- },
195
- "32021": {
196
- "content": "<extra_id_78>",
197
- "lstrip": false,
198
- "normalized": false,
199
- "rstrip": false,
200
- "single_word": false,
201
- "special": true
202
- },
203
- "32022": {
204
- "content": "<extra_id_77>",
205
- "lstrip": false,
206
- "normalized": false,
207
- "rstrip": false,
208
- "single_word": false,
209
- "special": true
210
- },
211
- "32023": {
212
- "content": "<extra_id_76>",
213
- "lstrip": false,
214
- "normalized": false,
215
- "rstrip": false,
216
- "single_word": false,
217
- "special": true
218
- },
219
- "32024": {
220
- "content": "<extra_id_75>",
221
- "lstrip": false,
222
- "normalized": false,
223
- "rstrip": false,
224
- "single_word": false,
225
- "special": true
226
- },
227
- "32025": {
228
- "content": "<extra_id_74>",
229
- "lstrip": false,
230
- "normalized": false,
231
- "rstrip": false,
232
- "single_word": false,
233
- "special": true
234
- },
235
- "32026": {
236
- "content": "<extra_id_73>",
237
- "lstrip": false,
238
- "normalized": false,
239
- "rstrip": false,
240
- "single_word": false,
241
- "special": true
242
- },
243
- "32027": {
244
- "content": "<extra_id_72>",
245
- "lstrip": false,
246
- "normalized": false,
247
- "rstrip": false,
248
- "single_word": false,
249
- "special": true
250
- },
251
- "32028": {
252
- "content": "<extra_id_71>",
253
- "lstrip": false,
254
- "normalized": false,
255
- "rstrip": false,
256
- "single_word": false,
257
- "special": true
258
- },
259
- "32029": {
260
- "content": "<extra_id_70>",
261
- "lstrip": false,
262
- "normalized": false,
263
- "rstrip": false,
264
- "single_word": false,
265
- "special": true
266
- },
267
- "32030": {
268
- "content": "<extra_id_69>",
269
- "lstrip": false,
270
- "normalized": false,
271
- "rstrip": false,
272
- "single_word": false,
273
- "special": true
274
- },
275
- "32031": {
276
- "content": "<extra_id_68>",
277
- "lstrip": false,
278
- "normalized": false,
279
- "rstrip": false,
280
- "single_word": false,
281
- "special": true
282
- },
283
- "32032": {
284
- "content": "<extra_id_67>",
285
- "lstrip": false,
286
- "normalized": false,
287
- "rstrip": false,
288
- "single_word": false,
289
- "special": true
290
- },
291
- "32033": {
292
- "content": "<extra_id_66>",
293
- "lstrip": false,
294
- "normalized": false,
295
- "rstrip": false,
296
- "single_word": false,
297
- "special": true
298
- },
299
- "32034": {
300
- "content": "<extra_id_65>",
301
- "lstrip": false,
302
- "normalized": false,
303
- "rstrip": false,
304
- "single_word": false,
305
- "special": true
306
- },
307
- "32035": {
308
- "content": "<extra_id_64>",
309
- "lstrip": false,
310
- "normalized": false,
311
- "rstrip": false,
312
- "single_word": false,
313
- "special": true
314
- },
315
- "32036": {
316
- "content": "<extra_id_63>",
317
- "lstrip": false,
318
- "normalized": false,
319
- "rstrip": false,
320
- "single_word": false,
321
- "special": true
322
- },
323
- "32037": {
324
- "content": "<extra_id_62>",
325
- "lstrip": false,
326
- "normalized": false,
327
- "rstrip": false,
328
- "single_word": false,
329
- "special": true
330
- },
331
- "32038": {
332
- "content": "<extra_id_61>",
333
- "lstrip": false,
334
- "normalized": false,
335
- "rstrip": false,
336
- "single_word": false,
337
- "special": true
338
- },
339
- "32039": {
340
- "content": "<extra_id_60>",
341
- "lstrip": false,
342
- "normalized": false,
343
- "rstrip": false,
344
- "single_word": false,
345
- "special": true
346
- },
347
- "32040": {
348
- "content": "<extra_id_59>",
349
- "lstrip": false,
350
- "normalized": false,
351
- "rstrip": false,
352
- "single_word": false,
353
- "special": true
354
- },
355
- "32041": {
356
- "content": "<extra_id_58>",
357
- "lstrip": false,
358
- "normalized": false,
359
- "rstrip": false,
360
- "single_word": false,
361
- "special": true
362
- },
363
- "32042": {
364
- "content": "<extra_id_57>",
365
- "lstrip": false,
366
- "normalized": false,
367
- "rstrip": false,
368
- "single_word": false,
369
- "special": true
370
- },
371
- "32043": {
372
- "content": "<extra_id_56>",
373
- "lstrip": false,
374
- "normalized": false,
375
- "rstrip": false,
376
- "single_word": false,
377
- "special": true
378
- },
379
- "32044": {
380
- "content": "<extra_id_55>",
381
- "lstrip": false,
382
- "normalized": false,
383
- "rstrip": false,
384
- "single_word": false,
385
- "special": true
386
- },
387
- "32045": {
388
- "content": "<extra_id_54>",
389
  "lstrip": false,
390
  "normalized": false,
391
  "rstrip": false,
392
  "single_word": false,
393
  "special": true
394
  },
395
- "32046": {
396
- "content": "<extra_id_53>",
397
  "lstrip": false,
398
  "normalized": false,
399
  "rstrip": false,
400
  "single_word": false,
401
  "special": true
402
  },
403
- "32047": {
404
- "content": "<extra_id_52>",
405
  "lstrip": false,
406
  "normalized": false,
407
  "rstrip": false,
408
  "single_word": false,
409
  "special": true
410
  },
411
- "32048": {
412
- "content": "<extra_id_51>",
413
  "lstrip": false,
414
  "normalized": false,
415
  "rstrip": false,
416
  "single_word": false,
417
  "special": true
418
  },
419
- "32049": {
420
- "content": "<extra_id_50>",
421
  "lstrip": false,
422
  "normalized": false,
423
  "rstrip": false,
424
  "single_word": false,
425
  "special": true
426
  },
427
- "32050": {
428
- "content": "<extra_id_49>",
429
  "lstrip": false,
430
  "normalized": false,
431
  "rstrip": false,
432
  "single_word": false,
433
  "special": true
434
  },
435
- "32051": {
436
- "content": "<extra_id_48>",
437
  "lstrip": false,
438
  "normalized": false,
439
  "rstrip": false,
440
  "single_word": false,
441
  "special": true
442
  },
443
- "32052": {
444
- "content": "<extra_id_47>",
445
  "lstrip": false,
446
  "normalized": false,
447
  "rstrip": false,
448
  "single_word": false,
449
  "special": true
450
  },
451
- "32053": {
452
- "content": "<extra_id_46>",
453
  "lstrip": false,
454
  "normalized": false,
455
  "rstrip": false,
456
  "single_word": false,
457
  "special": true
458
  },
459
- "32054": {
460
- "content": "<extra_id_45>",
461
  "lstrip": false,
462
  "normalized": false,
463
  "rstrip": false,
464
  "single_word": false,
465
  "special": true
466
  },
467
- "32055": {
468
- "content": "<extra_id_44>",
469
  "lstrip": false,
470
  "normalized": false,
471
  "rstrip": false,
472
  "single_word": false,
473
  "special": true
474
  },
475
- "32056": {
476
- "content": "<extra_id_43>",
477
  "lstrip": false,
478
  "normalized": false,
479
  "rstrip": false,
480
  "single_word": false,
481
  "special": true
482
  },
483
- "32057": {
484
- "content": "<extra_id_42>",
485
  "lstrip": false,
486
  "normalized": false,
487
  "rstrip": false,
488
  "single_word": false,
489
  "special": true
490
  },
491
- "32058": {
492
- "content": "<extra_id_41>",
493
  "lstrip": false,
494
  "normalized": false,
495
  "rstrip": false,
496
  "single_word": false,
497
  "special": true
498
  },
499
- "32059": {
500
- "content": "<extra_id_40>",
501
  "lstrip": false,
502
  "normalized": false,
503
  "rstrip": false,
504
  "single_word": false,
505
  "special": true
506
  },
507
- "32060": {
508
- "content": "<extra_id_39>",
509
  "lstrip": false,
510
  "normalized": false,
511
  "rstrip": false,
512
  "single_word": false,
513
  "special": true
514
  },
515
- "32061": {
516
- "content": "<extra_id_38>",
517
  "lstrip": false,
518
  "normalized": false,
519
  "rstrip": false,
520
  "single_word": false,
521
  "special": true
522
  },
523
- "32062": {
524
- "content": "<extra_id_37>",
525
  "lstrip": false,
526
  "normalized": false,
527
  "rstrip": false,
528
  "single_word": false,
529
  "special": true
530
  },
531
- "32063": {
532
- "content": "<extra_id_36>",
533
  "lstrip": false,
534
  "normalized": false,
535
  "rstrip": false,
536
  "single_word": false,
537
  "special": true
538
  },
539
- "32064": {
540
- "content": "<extra_id_35>",
541
  "lstrip": false,
542
  "normalized": false,
543
  "rstrip": false,
544
  "single_word": false,
545
  "special": true
546
  },
547
- "32065": {
548
- "content": "<extra_id_34>",
549
  "lstrip": false,
550
  "normalized": false,
551
  "rstrip": false,
552
  "single_word": false,
553
  "special": true
554
  },
555
- "32066": {
556
- "content": "<extra_id_33>",
557
  "lstrip": false,
558
  "normalized": false,
559
  "rstrip": false,
560
  "single_word": false,
561
  "special": true
562
  },
563
- "32067": {
564
- "content": "<extra_id_32>",
565
  "lstrip": false,
566
  "normalized": false,
567
  "rstrip": false,
568
  "single_word": false,
569
  "special": true
570
  },
571
- "32068": {
572
- "content": "<extra_id_31>",
573
  "lstrip": false,
574
  "normalized": false,
575
  "rstrip": false,
576
  "single_word": false,
577
  "special": true
578
  },
579
- "32069": {
580
- "content": "<extra_id_30>",
581
  "lstrip": false,
582
  "normalized": false,
583
  "rstrip": false,
584
  "single_word": false,
585
  "special": true
586
  },
587
- "32070": {
588
- "content": "<extra_id_29>",
589
  "lstrip": false,
590
  "normalized": false,
591
  "rstrip": false,
592
  "single_word": false,
593
  "special": true
594
  },
595
- "32071": {
596
- "content": "<extra_id_28>",
597
  "lstrip": false,
598
  "normalized": false,
599
  "rstrip": false,
600
  "single_word": false,
601
  "special": true
602
  },
603
- "32072": {
604
- "content": "<extra_id_27>",
605
  "lstrip": false,
606
  "normalized": false,
607
  "rstrip": false,
608
  "single_word": false,
609
  "special": true
610
  },
611
- "32073": {
612
- "content": "<extra_id_26>",
613
  "lstrip": false,
614
  "normalized": false,
615
  "rstrip": false,
616
  "single_word": false,
617
  "special": true
618
  },
619
- "32074": {
620
- "content": "<extra_id_25>",
621
  "lstrip": false,
622
  "normalized": false,
623
  "rstrip": false,
624
  "single_word": false,
625
  "special": true
626
  },
627
- "32075": {
628
- "content": "<extra_id_24>",
629
  "lstrip": false,
630
  "normalized": false,
631
  "rstrip": false,
632
  "single_word": false,
633
  "special": true
634
  },
635
- "32076": {
636
- "content": "<extra_id_23>",
637
  "lstrip": false,
638
  "normalized": false,
639
  "rstrip": false,
640
  "single_word": false,
641
  "special": true
642
  },
643
- "32077": {
644
- "content": "<extra_id_22>",
645
  "lstrip": false,
646
  "normalized": false,
647
  "rstrip": false,
648
  "single_word": false,
649
  "special": true
650
  },
651
- "32078": {
652
- "content": "<extra_id_21>",
653
  "lstrip": false,
654
  "normalized": false,
655
  "rstrip": false,
656
  "single_word": false,
657
  "special": true
658
  },
659
- "32079": {
660
- "content": "<extra_id_20>",
661
  "lstrip": false,
662
  "normalized": false,
663
  "rstrip": false,
664
  "single_word": false,
665
  "special": true
666
  },
667
- "32080": {
668
- "content": "<extra_id_19>",
669
  "lstrip": false,
670
  "normalized": false,
671
  "rstrip": false,
672
  "single_word": false,
673
  "special": true
674
  },
675
- "32081": {
676
- "content": "<extra_id_18>",
677
  "lstrip": false,
678
  "normalized": false,
679
  "rstrip": false,
680
  "single_word": false,
681
  "special": true
682
  },
683
- "32082": {
684
- "content": "<extra_id_17>",
685
  "lstrip": false,
686
  "normalized": false,
687
  "rstrip": false,
688
  "single_word": false,
689
  "special": true
690
  },
691
- "32083": {
692
- "content": "<extra_id_16>",
693
  "lstrip": false,
694
  "normalized": false,
695
  "rstrip": false,
696
  "single_word": false,
697
  "special": true
698
  },
699
- "32084": {
700
- "content": "<extra_id_15>",
701
  "lstrip": false,
702
  "normalized": false,
703
  "rstrip": false,
704
  "single_word": false,
705
  "special": true
706
  },
707
- "32085": {
708
- "content": "<extra_id_14>",
709
  "lstrip": false,
710
  "normalized": false,
711
  "rstrip": false,
712
  "single_word": false,
713
  "special": true
714
  },
715
- "32086": {
716
- "content": "<extra_id_13>",
717
  "lstrip": false,
718
  "normalized": false,
719
  "rstrip": false,
720
  "single_word": false,
721
  "special": true
722
  },
723
- "32087": {
724
- "content": "<extra_id_12>",
725
  "lstrip": false,
726
  "normalized": false,
727
  "rstrip": false,
728
  "single_word": false,
729
  "special": true
730
  },
731
- "32088": {
732
- "content": "<extra_id_11>",
733
  "lstrip": false,
734
  "normalized": false,
735
  "rstrip": false,
736
  "single_word": false,
737
  "special": true
738
  },
739
- "32089": {
740
- "content": "<extra_id_10>",
741
  "lstrip": false,
742
  "normalized": false,
743
  "rstrip": false,
744
  "single_word": false,
745
  "special": true
746
  },
747
- "32090": {
748
- "content": "<extra_id_9>",
749
  "lstrip": false,
750
  "normalized": false,
751
  "rstrip": false,
752
  "single_word": false,
753
  "special": true
754
  },
755
- "32091": {
756
- "content": "<extra_id_8>",
757
  "lstrip": false,
758
  "normalized": false,
759
  "rstrip": false,
760
  "single_word": false,
761
  "special": true
762
  },
763
- "32092": {
764
- "content": "<extra_id_7>",
765
  "lstrip": false,
766
  "normalized": false,
767
  "rstrip": false,
768
  "single_word": false,
769
  "special": true
770
  },
771
- "32093": {
772
- "content": "<extra_id_6>",
773
  "lstrip": false,
774
  "normalized": false,
775
  "rstrip": false,
776
  "single_word": false,
777
  "special": true
778
  },
779
- "32094": {
780
- "content": "<extra_id_5>",
781
  "lstrip": false,
782
  "normalized": false,
783
  "rstrip": false,
784
  "single_word": false,
785
  "special": true
786
  },
787
- "32095": {
788
- "content": "<extra_id_4>",
789
  "lstrip": false,
790
  "normalized": false,
791
  "rstrip": false,
792
  "single_word": false,
793
  "special": true
794
  },
795
- "32096": {
796
- "content": "<extra_id_3>",
797
  "lstrip": false,
798
  "normalized": false,
799
  "rstrip": false,
800
  "single_word": false,
801
  "special": true
802
  },
803
- "32097": {
804
- "content": "<extra_id_2>",
805
  "lstrip": false,
806
  "normalized": false,
807
  "rstrip": false,
808
  "single_word": false,
809
  "special": true
810
  },
811
- "32098": {
812
- "content": "<extra_id_1>",
813
  "lstrip": false,
814
  "normalized": false,
815
  "rstrip": false,
816
  "single_word": false,
817
  "special": true
818
  },
819
- "32099": {
820
- "content": "<extra_id_0>",
821
- "lstrip": false,
822
- "normalized": false,
823
  "rstrip": false,
824
  "single_word": false,
825
  "special": true
826
  }
827
  },
828
  "additional_special_tokens": [
829
- "<extra_id_0>",
830
- "<extra_id_1>",
831
- "<extra_id_2>",
832
- "<extra_id_3>",
833
- "<extra_id_4>",
834
- "<extra_id_5>",
835
- "<extra_id_6>",
836
- "<extra_id_7>",
837
- "<extra_id_8>",
838
- "<extra_id_9>",
839
- "<extra_id_10>",
840
- "<extra_id_11>",
841
- "<extra_id_12>",
842
- "<extra_id_13>",
843
- "<extra_id_14>",
844
- "<extra_id_15>",
845
- "<extra_id_16>",
846
- "<extra_id_17>",
847
- "<extra_id_18>",
848
- "<extra_id_19>",
849
- "<extra_id_20>",
850
- "<extra_id_21>",
851
- "<extra_id_22>",
852
- "<extra_id_23>",
853
- "<extra_id_24>",
854
- "<extra_id_25>",
855
- "<extra_id_26>",
856
- "<extra_id_27>",
857
- "<extra_id_28>",
858
- "<extra_id_29>",
859
- "<extra_id_30>",
860
- "<extra_id_31>",
861
- "<extra_id_32>",
862
- "<extra_id_33>",
863
- "<extra_id_34>",
864
- "<extra_id_35>",
865
- "<extra_id_36>",
866
- "<extra_id_37>",
867
- "<extra_id_38>",
868
- "<extra_id_39>",
869
- "<extra_id_40>",
870
- "<extra_id_41>",
871
- "<extra_id_42>",
872
- "<extra_id_43>",
873
- "<extra_id_44>",
874
- "<extra_id_45>",
875
- "<extra_id_46>",
876
- "<extra_id_47>",
877
- "<extra_id_48>",
878
- "<extra_id_49>",
879
- "<extra_id_50>",
880
- "<extra_id_51>",
881
- "<extra_id_52>",
882
- "<extra_id_53>",
883
- "<extra_id_54>",
884
- "<extra_id_55>",
885
- "<extra_id_56>",
886
- "<extra_id_57>",
887
- "<extra_id_58>",
888
- "<extra_id_59>",
889
- "<extra_id_60>",
890
- "<extra_id_61>",
891
- "<extra_id_62>",
892
- "<extra_id_63>",
893
- "<extra_id_64>",
894
- "<extra_id_65>",
895
- "<extra_id_66>",
896
- "<extra_id_67>",
897
- "<extra_id_68>",
898
- "<extra_id_69>",
899
- "<extra_id_70>",
900
- "<extra_id_71>",
901
- "<extra_id_72>",
902
- "<extra_id_73>",
903
- "<extra_id_74>",
904
- "<extra_id_75>",
905
- "<extra_id_76>",
906
- "<extra_id_77>",
907
- "<extra_id_78>",
908
- "<extra_id_79>",
909
- "<extra_id_80>",
910
- "<extra_id_81>",
911
- "<extra_id_82>",
912
- "<extra_id_83>",
913
- "<extra_id_84>",
914
- "<extra_id_85>",
915
- "<extra_id_86>",
916
- "<extra_id_87>",
917
- "<extra_id_88>",
918
- "<extra_id_89>",
919
- "<extra_id_90>",
920
- "<extra_id_91>",
921
- "<extra_id_92>",
922
- "<extra_id_93>",
923
- "<extra_id_94>",
924
- "<extra_id_95>",
925
- "<extra_id_96>",
926
- "<extra_id_97>",
927
- "<extra_id_98>",
928
- "<extra_id_99>"
929
  ],
 
930
  "clean_up_tokenization_spaces": true,
 
931
  "eos_token": "</s>",
932
- "extra_ids": 100,
933
- "model_max_length": 512,
934
  "pad_token": "<pad>",
 
935
  "sp_model_kwargs": {},
936
- "tokenizer_class": "T5Tokenizer",
 
 
937
  "unk_token": "<unk>"
938
  }
 
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
+ "content": "<s>",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
 
9
  "special": true
10
  },
11
  "1": {
12
+ "content": "<pad>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": 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
+ "250001": {
36
+ "content": "ar_AR",
37
  "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
42
  },
43
+ "250002": {
44
+ "content": "cs_CZ",
45
  "lstrip": false,
46
  "normalized": false,
47
  "rstrip": false,
48
  "single_word": false,
49
  "special": true
50
  },
51
+ "250003": {
52
+ "content": "de_DE",
53
  "lstrip": false,
54
  "normalized": false,
55
  "rstrip": false,
56
  "single_word": false,
57
  "special": true
58
  },
59
+ "250004": {
60
+ "content": "en_XX",
61
  "lstrip": false,
62
  "normalized": false,
63
  "rstrip": false,
64
  "single_word": false,
65
  "special": true
66
  },
67
+ "250005": {
68
+ "content": "es_XX",
69
  "lstrip": false,
70
  "normalized": false,
71
  "rstrip": false,
72
  "single_word": false,
73
  "special": true
74
  },
75
+ "250006": {
76
+ "content": "et_EE",
77
  "lstrip": false,
78
  "normalized": false,
79
  "rstrip": false,
80
  "single_word": false,
81
  "special": true
82
  },
83
+ "250007": {
84
+ "content": "fi_FI",
85
  "lstrip": false,
86
  "normalized": false,
87
  "rstrip": false,
88
  "single_word": false,
89
  "special": true
90
  },
91
+ "250008": {
92
+ "content": "fr_XX",
93
  "lstrip": false,
94
  "normalized": false,
95
  "rstrip": false,
96
  "single_word": false,
97
  "special": true
98
  },
99
+ "250009": {
100
+ "content": "gu_IN",
101
  "lstrip": false,
102
  "normalized": false,
103
  "rstrip": false,
104
  "single_word": false,
105
  "special": true
106
  },
107
+ "250010": {
108
+ "content": "hi_IN",
109
  "lstrip": false,
110
  "normalized": false,
111
  "rstrip": false,
112
  "single_word": false,
113
  "special": true
114
  },
115
+ "250011": {
116
+ "content": "it_IT",
117
  "lstrip": false,
118
  "normalized": false,
119
  "rstrip": false,
120
  "single_word": false,
121
  "special": true
122
  },
123
+ "250012": {
124
+ "content": "ja_XX",
125
  "lstrip": false,
126
  "normalized": false,
127
  "rstrip": false,
128
  "single_word": false,
129
  "special": true
130
  },
131
+ "250013": {
132
+ "content": "kk_KZ",
133
  "lstrip": false,
134
  "normalized": false,
135
  "rstrip": false,
136
  "single_word": false,
137
  "special": true
138
  },
139
+ "250014": {
140
+ "content": "ko_KR",
141
  "lstrip": false,
142
  "normalized": false,
143
  "rstrip": false,
144
  "single_word": false,
145
  "special": true
146
  },
147
+ "250015": {
148
+ "content": "lt_LT",
149
  "lstrip": false,
150
  "normalized": false,
151
  "rstrip": false,
152
  "single_word": false,
153
  "special": true
154
  },
155
+ "250016": {
156
+ "content": "lv_LV",
157
  "lstrip": false,
158
  "normalized": false,
159
  "rstrip": false,
160
  "single_word": false,
161
  "special": true
162
  },
163
+ "250017": {
164
+ "content": "my_MM",
165
  "lstrip": false,
166
  "normalized": false,
167
  "rstrip": false,
168
  "single_word": false,
169
  "special": true
170
  },
171
+ "250018": {
172
+ "content": "ne_NP",
173
  "lstrip": false,
174
  "normalized": false,
175
  "rstrip": false,
176
  "single_word": false,
177
  "special": true
178
  },
179
+ "250019": {
180
+ "content": "nl_XX",
181
  "lstrip": false,
182
  "normalized": false,
183
  "rstrip": false,
184
  "single_word": false,
185
  "special": true
186
  },
187
+ "250020": {
188
+ "content": "ro_RO",
189
  "lstrip": false,
190
  "normalized": false,
191
  "rstrip": false,
192
  "single_word": false,
193
  "special": true
194
  },
195
+ "250021": {
196
+ "content": "ru_RU",
197
  "lstrip": false,
198
  "normalized": false,
199
  "rstrip": false,
200
  "single_word": false,
201
  "special": true
202
  },
203
+ "250022": {
204
+ "content": "si_LK",
205
  "lstrip": false,
206
  "normalized": false,
207
  "rstrip": false,
208
  "single_word": false,
209
  "special": true
210
  },
211
+ "250023": {
212
+ "content": "tr_TR",
213
  "lstrip": false,
214
  "normalized": false,
215
  "rstrip": false,
216
  "single_word": false,
217
  "special": true
218
  },
219
+ "250024": {
220
+ "content": "vi_VN",
221
  "lstrip": false,
222
  "normalized": false,
223
  "rstrip": false,
224
  "single_word": false,
225
  "special": true
226
  },
227
+ "250025": {
228
+ "content": "zh_CN",
229
  "lstrip": false,
230
  "normalized": false,
231
  "rstrip": false,
232
  "single_word": false,
233
  "special": true
234
  },
235
+ "250026": {
236
+ "content": "af_ZA",
237
  "lstrip": false,
238
  "normalized": false,
239
  "rstrip": false,
240
  "single_word": false,
241
  "special": true
242
  },
243
+ "250027": {
244
+ "content": "az_AZ",
245
  "lstrip": false,
246
  "normalized": false,
247
  "rstrip": false,
248
  "single_word": false,
249
  "special": true
250
  },
251
+ "250028": {
252
+ "content": "bn_IN",
253
  "lstrip": false,
254
  "normalized": false,
255
  "rstrip": false,
256
  "single_word": false,
257
  "special": true
258
  },
259
+ "250029": {
260
+ "content": "fa_IR",
261
  "lstrip": false,
262
  "normalized": false,
263
  "rstrip": false,
264
  "single_word": false,
265
  "special": true
266
  },
267
+ "250030": {
268
+ "content": "he_IL",
269
  "lstrip": false,
270
  "normalized": false,
271
  "rstrip": false,
272
  "single_word": false,
273
  "special": true
274
  },
275
+ "250031": {
276
+ "content": "hr_HR",
277
  "lstrip": false,
278
  "normalized": false,
279
  "rstrip": false,
280
  "single_word": false,
281
  "special": true
282
  },
283
+ "250032": {
284
+ "content": "id_ID",
285
  "lstrip": false,
286
  "normalized": false,
287
  "rstrip": false,
288
  "single_word": false,
289
  "special": true
290
  },
291
+ "250033": {
292
+ "content": "ka_GE",
293
  "lstrip": false,
294
  "normalized": false,
295
  "rstrip": false,
296
  "single_word": false,
297
  "special": true
298
  },
299
+ "250034": {
300
+ "content": "km_KH",
301
  "lstrip": false,
302
  "normalized": false,
303
  "rstrip": false,
304
  "single_word": false,
305
  "special": true
306
  },
307
+ "250035": {
308
+ "content": "mk_MK",
309
  "lstrip": false,
310
  "normalized": false,
311
  "rstrip": false,
312
  "single_word": false,
313
  "special": true
314
  },
315
+ "250036": {
316
+ "content": "ml_IN",
317
  "lstrip": false,
318
  "normalized": false,
319
  "rstrip": false,
320
  "single_word": false,
321
  "special": true
322
  },
323
+ "250037": {
324
+ "content": "mn_MN",
325
  "lstrip": false,
326
  "normalized": false,
327
  "rstrip": false,
328
  "single_word": false,
329
  "special": true
330
  },
331
+ "250038": {
332
+ "content": "mr_IN",
333
  "lstrip": false,
334
  "normalized": false,
335
  "rstrip": false,
336
  "single_word": false,
337
  "special": true
338
  },
339
+ "250039": {
340
+ "content": "pl_PL",
341
  "lstrip": false,
342
  "normalized": false,
343
  "rstrip": false,
344
  "single_word": false,
345
  "special": true
346
  },
347
+ "250040": {
348
+ "content": "ps_AF",
349
  "lstrip": false,
350
  "normalized": false,
351
  "rstrip": false,
352
  "single_word": false,
353
  "special": true
354
  },
355
+ "250041": {
356
+ "content": "pt_XX",
357
  "lstrip": false,
358
  "normalized": false,
359
  "rstrip": false,
360
  "single_word": false,
361
  "special": true
362
  },
363
+ "250042": {
364
+ "content": "sv_SE",
365
  "lstrip": false,
366
  "normalized": false,
367
  "rstrip": false,
368
  "single_word": false,
369
  "special": true
370
  },
371
+ "250043": {
372
+ "content": "sw_KE",
373
  "lstrip": false,
374
  "normalized": false,
375
  "rstrip": false,
376
  "single_word": false,
377
  "special": true
378
  },
379
+ "250044": {
380
+ "content": "ta_IN",
381
  "lstrip": false,
382
  "normalized": false,
383
  "rstrip": false,
384
  "single_word": false,
385
  "special": true
386
  },
387
+ "250045": {
388
+ "content": "te_IN",
389
  "lstrip": false,
390
  "normalized": false,
391
  "rstrip": false,
392
  "single_word": false,
393
  "special": true
394
  },
395
+ "250046": {
396
+ "content": "th_TH",
397
  "lstrip": false,
398
  "normalized": false,
399
  "rstrip": false,
400
  "single_word": false,
401
  "special": true
402
  },
403
+ "250047": {
404
+ "content": "tl_XX",
405
  "lstrip": false,
406
  "normalized": false,
407
  "rstrip": false,
408
  "single_word": false,
409
  "special": true
410
  },
411
+ "250048": {
412
+ "content": "uk_UA",
413
  "lstrip": false,
414
  "normalized": false,
415
  "rstrip": false,
416
  "single_word": false,
417
  "special": true
418
  },
419
+ "250049": {
420
+ "content": "ur_PK",
421
  "lstrip": false,
422
  "normalized": false,
423
  "rstrip": false,
424
  "single_word": false,
425
  "special": true
426
  },
427
+ "250050": {
428
+ "content": "xh_ZA",
429
  "lstrip": false,
430
  "normalized": false,
431
  "rstrip": false,
432
  "single_word": false,
433
  "special": true
434
  },
435
+ "250051": {
436
+ "content": "gl_ES",
437
  "lstrip": false,
438
  "normalized": false,
439
  "rstrip": false,
440
  "single_word": false,
441
  "special": true
442
  },
443
+ "250052": {
444
+ "content": "sl_SI",
445
  "lstrip": false,
446
  "normalized": false,
447
  "rstrip": false,
448
  "single_word": false,
449
  "special": true
450
  },
451
+ "250053": {
452
+ "content": "<mask>",
453
+ "lstrip": true,
454
+ "normalized": true,
455
  "rstrip": false,
456
  "single_word": false,
457
  "special": true
458
  }
459
  },
460
  "additional_special_tokens": [
461
+ "ar_AR",
462
+ "cs_CZ",
463
+ "de_DE",
464
+ "en_XX",
465
+ "es_XX",
466
+ "et_EE",
467
+ "fi_FI",
468
+ "fr_XX",
469
+ "gu_IN",
470
+ "hi_IN",
471
+ "it_IT",
472
+ "ja_XX",
473
+ "kk_KZ",
474
+ "ko_KR",
475
+ "lt_LT",
476
+ "lv_LV",
477
+ "my_MM",
478
+ "ne_NP",
479
+ "nl_XX",
480
+ "ro_RO",
481
+ "ru_RU",
482
+ "si_LK",
483
+ "tr_TR",
484
+ "vi_VN",
485
+ "zh_CN",
486
+ "af_ZA",
487
+ "az_AZ",
488
+ "bn_IN",
489
+ "fa_IR",
490
+ "he_IL",
491
+ "hr_HR",
492
+ "id_ID",
493
+ "ka_GE",
494
+ "km_KH",
495
+ "mk_MK",
496
+ "ml_IN",
497
+ "mn_MN",
498
+ "mr_IN",
499
+ "pl_PL",
500
+ "ps_AF",
501
+ "pt_XX",
502
+ "sv_SE",
503
+ "sw_KE",
504
+ "ta_IN",
505
+ "te_IN",
506
+ "th_TH",
507
+ "tl_XX",
508
+ "uk_UA",
509
+ "ur_PK",
510
+ "xh_ZA",
511
+ "gl_ES",
512
+ "sl_SI"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
513
  ],
514
+ "bos_token": "<s>",
515
  "clean_up_tokenization_spaces": true,
516
+ "cls_token": "<s>",
517
  "eos_token": "</s>",
518
+ "mask_token": "<mask>",
519
+ "model_max_length": 1024,
520
  "pad_token": "<pad>",
521
+ "sep_token": "</s>",
522
  "sp_model_kwargs": {},
523
+ "src_lang": "en_XX",
524
+ "tgt_lang": null,
525
+ "tokenizer_class": "MBart50Tokenizer",
526
  "unk_token": "<unk>"
527
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2e9228c0b7cd8ff45d33c16939eb5d9cbcaeb595981077d59ede3f24a4d2c80
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2b365a0739efde9efcff0895c6800d8fe946c1acdc92469551ccf8f17fa8aa0
3
  size 4856