Upload 7 files
Browse files- config.json +35 -0
- generation_config.json +9 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +138 -0
- tokenizer.json +1898 -0
- tokenizer_config.json +1054 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./mt5_transliteration_upgraded/checkpoint-96802",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MT5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 811,
|
| 7 |
+
"classifier_dropout": 0.0,
|
| 8 |
+
"d_ff": 1024,
|
| 9 |
+
"d_kv": 64,
|
| 10 |
+
"d_model": 512,
|
| 11 |
+
"decoder_start_token_id": 813,
|
| 12 |
+
"dense_act_fn": "gelu_new",
|
| 13 |
+
"dropout_rate": 0.1,
|
| 14 |
+
"early_stopping": true,
|
| 15 |
+
"eos_token_id": 812,
|
| 16 |
+
"feed_forward_proj": "gated-gelu",
|
| 17 |
+
"initializer_factor": 1.0,
|
| 18 |
+
"is_encoder_decoder": true,
|
| 19 |
+
"is_gated_act": true,
|
| 20 |
+
"layer_norm_epsilon": 1e-06,
|
| 21 |
+
"max_length": 64,
|
| 22 |
+
"model_type": "mt5",
|
| 23 |
+
"num_decoder_layers": 4,
|
| 24 |
+
"num_heads": 4,
|
| 25 |
+
"num_layers": 4,
|
| 26 |
+
"pad_token_id": 813,
|
| 27 |
+
"relative_attention_max_distance": 128,
|
| 28 |
+
"relative_attention_num_buckets": 32,
|
| 29 |
+
"tie_word_embeddings": false,
|
| 30 |
+
"tokenizer_class": "T5Tokenizer",
|
| 31 |
+
"torch_dtype": "float32",
|
| 32 |
+
"transformers_version": "4.30.2",
|
| 33 |
+
"use_cache": true,
|
| 34 |
+
"vocab_size": 826
|
| 35 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 811,
|
| 3 |
+
"decoder_start_token_id": 813,
|
| 4 |
+
"early_stopping": true,
|
| 5 |
+
"eos_token_id": 812,
|
| 6 |
+
"max_length": 64,
|
| 7 |
+
"pad_token_id": 813,
|
| 8 |
+
"transformers_version": "4.30.2"
|
| 9 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eea47c12a0b8ec05665d7b4d1882605d7cc842199e8dbdf8a94e610957015c41
|
| 3 |
+
size 78959231
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,138 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<arb>",
|
| 4 |
+
"<asm>",
|
| 5 |
+
"<ben>",
|
| 6 |
+
"<guj>",
|
| 7 |
+
"<hin>",
|
| 8 |
+
"<kan>",
|
| 9 |
+
"<mal>",
|
| 10 |
+
"<mar>",
|
| 11 |
+
"<ori>",
|
| 12 |
+
"<pan>",
|
| 13 |
+
"<tam>",
|
| 14 |
+
"<tel>",
|
| 15 |
+
"<extra_id_0>",
|
| 16 |
+
"<extra_id_1>",
|
| 17 |
+
"<extra_id_2>",
|
| 18 |
+
"<extra_id_3>",
|
| 19 |
+
"<extra_id_4>",
|
| 20 |
+
"<extra_id_5>",
|
| 21 |
+
"<extra_id_6>",
|
| 22 |
+
"<extra_id_7>",
|
| 23 |
+
"<extra_id_8>",
|
| 24 |
+
"<extra_id_9>",
|
| 25 |
+
"<extra_id_10>",
|
| 26 |
+
"<extra_id_11>",
|
| 27 |
+
"<extra_id_12>",
|
| 28 |
+
"<extra_id_13>",
|
| 29 |
+
"<extra_id_14>",
|
| 30 |
+
"<extra_id_15>",
|
| 31 |
+
"<extra_id_16>",
|
| 32 |
+
"<extra_id_17>",
|
| 33 |
+
"<extra_id_18>",
|
| 34 |
+
"<extra_id_19>",
|
| 35 |
+
"<extra_id_20>",
|
| 36 |
+
"<extra_id_21>",
|
| 37 |
+
"<extra_id_22>",
|
| 38 |
+
"<extra_id_23>",
|
| 39 |
+
"<extra_id_24>",
|
| 40 |
+
"<extra_id_25>",
|
| 41 |
+
"<extra_id_26>",
|
| 42 |
+
"<extra_id_27>",
|
| 43 |
+
"<extra_id_28>",
|
| 44 |
+
"<extra_id_29>",
|
| 45 |
+
"<extra_id_30>",
|
| 46 |
+
"<extra_id_31>",
|
| 47 |
+
"<extra_id_32>",
|
| 48 |
+
"<extra_id_33>",
|
| 49 |
+
"<extra_id_34>",
|
| 50 |
+
"<extra_id_35>",
|
| 51 |
+
"<extra_id_36>",
|
| 52 |
+
"<extra_id_37>",
|
| 53 |
+
"<extra_id_38>",
|
| 54 |
+
"<extra_id_39>",
|
| 55 |
+
"<extra_id_40>",
|
| 56 |
+
"<extra_id_41>",
|
| 57 |
+
"<extra_id_42>",
|
| 58 |
+
"<extra_id_43>",
|
| 59 |
+
"<extra_id_44>",
|
| 60 |
+
"<extra_id_45>",
|
| 61 |
+
"<extra_id_46>",
|
| 62 |
+
"<extra_id_47>",
|
| 63 |
+
"<extra_id_48>",
|
| 64 |
+
"<extra_id_49>",
|
| 65 |
+
"<extra_id_50>",
|
| 66 |
+
"<extra_id_51>",
|
| 67 |
+
"<extra_id_52>",
|
| 68 |
+
"<extra_id_53>",
|
| 69 |
+
"<extra_id_54>",
|
| 70 |
+
"<extra_id_55>",
|
| 71 |
+
"<extra_id_56>",
|
| 72 |
+
"<extra_id_57>",
|
| 73 |
+
"<extra_id_58>",
|
| 74 |
+
"<extra_id_59>",
|
| 75 |
+
"<extra_id_60>",
|
| 76 |
+
"<extra_id_61>",
|
| 77 |
+
"<extra_id_62>",
|
| 78 |
+
"<extra_id_63>",
|
| 79 |
+
"<extra_id_64>",
|
| 80 |
+
"<extra_id_65>",
|
| 81 |
+
"<extra_id_66>",
|
| 82 |
+
"<extra_id_67>",
|
| 83 |
+
"<extra_id_68>",
|
| 84 |
+
"<extra_id_69>",
|
| 85 |
+
"<extra_id_70>",
|
| 86 |
+
"<extra_id_71>",
|
| 87 |
+
"<extra_id_72>",
|
| 88 |
+
"<extra_id_73>",
|
| 89 |
+
"<extra_id_74>",
|
| 90 |
+
"<extra_id_75>",
|
| 91 |
+
"<extra_id_76>",
|
| 92 |
+
"<extra_id_77>",
|
| 93 |
+
"<extra_id_78>",
|
| 94 |
+
"<extra_id_79>",
|
| 95 |
+
"<extra_id_80>",
|
| 96 |
+
"<extra_id_81>",
|
| 97 |
+
"<extra_id_82>",
|
| 98 |
+
"<extra_id_83>",
|
| 99 |
+
"<extra_id_84>",
|
| 100 |
+
"<extra_id_85>",
|
| 101 |
+
"<extra_id_86>",
|
| 102 |
+
"<extra_id_87>",
|
| 103 |
+
"<extra_id_88>",
|
| 104 |
+
"<extra_id_89>",
|
| 105 |
+
"<extra_id_90>",
|
| 106 |
+
"<extra_id_91>",
|
| 107 |
+
"<extra_id_92>",
|
| 108 |
+
"<extra_id_93>",
|
| 109 |
+
"<extra_id_94>",
|
| 110 |
+
"<extra_id_95>",
|
| 111 |
+
"<extra_id_96>",
|
| 112 |
+
"<extra_id_97>",
|
| 113 |
+
"<extra_id_98>",
|
| 114 |
+
"<extra_id_99>"
|
| 115 |
+
],
|
| 116 |
+
"bos_token": {
|
| 117 |
+
"content": "<s>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false
|
| 122 |
+
},
|
| 123 |
+
"eos_token": {
|
| 124 |
+
"content": "</s>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false
|
| 129 |
+
},
|
| 130 |
+
"pad_token": {
|
| 131 |
+
"content": "<pad>",
|
| 132 |
+
"lstrip": false,
|
| 133 |
+
"normalized": false,
|
| 134 |
+
"rstrip": false,
|
| 135 |
+
"single_word": false
|
| 136 |
+
},
|
| 137 |
+
"unk_token": "<unk>"
|
| 138 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,1898 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": {
|
| 5 |
+
"strategy": "BatchLongest",
|
| 6 |
+
"direction": "Right",
|
| 7 |
+
"pad_to_multiple_of": null,
|
| 8 |
+
"pad_id": 813,
|
| 9 |
+
"pad_type_id": 0,
|
| 10 |
+
"pad_token": "<pad>"
|
| 11 |
+
},
|
| 12 |
+
"added_tokens": [
|
| 13 |
+
{
|
| 14 |
+
"id": 0,
|
| 15 |
+
"content": "<unk>",
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"lstrip": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"id": 811,
|
| 24 |
+
"content": "<s>",
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"normalized": false,
|
| 29 |
+
"special": true
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"id": 812,
|
| 33 |
+
"content": "</s>",
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"lstrip": false,
|
| 36 |
+
"rstrip": false,
|
| 37 |
+
"normalized": false,
|
| 38 |
+
"special": true
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"id": 813,
|
| 42 |
+
"content": "<pad>",
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"lstrip": false,
|
| 45 |
+
"rstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"special": true
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"id": 814,
|
| 51 |
+
"content": "<arb>",
|
| 52 |
+
"single_word": false,
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"rstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"special": true
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"id": 815,
|
| 60 |
+
"content": "<asm>",
|
| 61 |
+
"single_word": false,
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"id": 816,
|
| 69 |
+
"content": "<ben>",
|
| 70 |
+
"single_word": false,
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"id": 817,
|
| 78 |
+
"content": "<guj>",
|
| 79 |
+
"single_word": false,
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"normalized": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"id": 818,
|
| 87 |
+
"content": "<hin>",
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"lstrip": false,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"normalized": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"id": 819,
|
| 96 |
+
"content": "<kan>",
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"lstrip": false,
|
| 99 |
+
"rstrip": false,
|
| 100 |
+
"normalized": false,
|
| 101 |
+
"special": true
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"id": 820,
|
| 105 |
+
"content": "<mal>",
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"lstrip": false,
|
| 108 |
+
"rstrip": false,
|
| 109 |
+
"normalized": false,
|
| 110 |
+
"special": true
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"id": 821,
|
| 114 |
+
"content": "<mar>",
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"lstrip": false,
|
| 117 |
+
"rstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"special": true
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"id": 822,
|
| 123 |
+
"content": "<ori>",
|
| 124 |
+
"single_word": false,
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"rstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"special": true
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"id": 823,
|
| 132 |
+
"content": "<pan>",
|
| 133 |
+
"single_word": false,
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"id": 824,
|
| 141 |
+
"content": "<tam>",
|
| 142 |
+
"single_word": false,
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"normalized": false,
|
| 146 |
+
"special": true
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"id": 825,
|
| 150 |
+
"content": "<tel>",
|
| 151 |
+
"single_word": false,
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"normalized": false,
|
| 155 |
+
"special": true
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"id": 826,
|
| 159 |
+
"content": "<extra_id_0>",
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"lstrip": false,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"normalized": false,
|
| 164 |
+
"special": true
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"id": 827,
|
| 168 |
+
"content": "<extra_id_1>",
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"lstrip": false,
|
| 171 |
+
"rstrip": false,
|
| 172 |
+
"normalized": false,
|
| 173 |
+
"special": true
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"id": 828,
|
| 177 |
+
"content": "<extra_id_2>",
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"lstrip": false,
|
| 180 |
+
"rstrip": false,
|
| 181 |
+
"normalized": false,
|
| 182 |
+
"special": true
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"id": 829,
|
| 186 |
+
"content": "<extra_id_3>",
|
| 187 |
+
"single_word": false,
|
| 188 |
+
"lstrip": false,
|
| 189 |
+
"rstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"special": true
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"id": 830,
|
| 195 |
+
"content": "<extra_id_4>",
|
| 196 |
+
"single_word": false,
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"rstrip": false,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"special": true
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"id": 831,
|
| 204 |
+
"content": "<extra_id_5>",
|
| 205 |
+
"single_word": false,
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"id": 832,
|
| 213 |
+
"content": "<extra_id_6>",
|
| 214 |
+
"single_word": false,
|
| 215 |
+
"lstrip": false,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"normalized": false,
|
| 218 |
+
"special": true
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"id": 833,
|
| 222 |
+
"content": "<extra_id_7>",
|
| 223 |
+
"single_word": false,
|
| 224 |
+
"lstrip": false,
|
| 225 |
+
"rstrip": false,
|
| 226 |
+
"normalized": false,
|
| 227 |
+
"special": true
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"id": 834,
|
| 231 |
+
"content": "<extra_id_8>",
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"lstrip": false,
|
| 234 |
+
"rstrip": false,
|
| 235 |
+
"normalized": false,
|
| 236 |
+
"special": true
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"id": 835,
|
| 240 |
+
"content": "<extra_id_9>",
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"lstrip": false,
|
| 243 |
+
"rstrip": false,
|
| 244 |
+
"normalized": false,
|
| 245 |
+
"special": true
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"id": 836,
|
| 249 |
+
"content": "<extra_id_10>",
|
| 250 |
+
"single_word": false,
|
| 251 |
+
"lstrip": false,
|
| 252 |
+
"rstrip": false,
|
| 253 |
+
"normalized": false,
|
| 254 |
+
"special": true
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"id": 837,
|
| 258 |
+
"content": "<extra_id_11>",
|
| 259 |
+
"single_word": false,
|
| 260 |
+
"lstrip": false,
|
| 261 |
+
"rstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"special": true
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"id": 838,
|
| 267 |
+
"content": "<extra_id_12>",
|
| 268 |
+
"single_word": false,
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"rstrip": false,
|
| 271 |
+
"normalized": false,
|
| 272 |
+
"special": true
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"id": 839,
|
| 276 |
+
"content": "<extra_id_13>",
|
| 277 |
+
"single_word": false,
|
| 278 |
+
"lstrip": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"normalized": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"id": 840,
|
| 285 |
+
"content": "<extra_id_14>",
|
| 286 |
+
"single_word": false,
|
| 287 |
+
"lstrip": false,
|
| 288 |
+
"rstrip": false,
|
| 289 |
+
"normalized": false,
|
| 290 |
+
"special": true
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"id": 841,
|
| 294 |
+
"content": "<extra_id_15>",
|
| 295 |
+
"single_word": false,
|
| 296 |
+
"lstrip": false,
|
| 297 |
+
"rstrip": false,
|
| 298 |
+
"normalized": false,
|
| 299 |
+
"special": true
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"id": 842,
|
| 303 |
+
"content": "<extra_id_16>",
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"lstrip": false,
|
| 306 |
+
"rstrip": false,
|
| 307 |
+
"normalized": false,
|
| 308 |
+
"special": true
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"id": 843,
|
| 312 |
+
"content": "<extra_id_17>",
|
| 313 |
+
"single_word": false,
|
| 314 |
+
"lstrip": false,
|
| 315 |
+
"rstrip": false,
|
| 316 |
+
"normalized": false,
|
| 317 |
+
"special": true
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"id": 844,
|
| 321 |
+
"content": "<extra_id_18>",
|
| 322 |
+
"single_word": false,
|
| 323 |
+
"lstrip": false,
|
| 324 |
+
"rstrip": false,
|
| 325 |
+
"normalized": false,
|
| 326 |
+
"special": true
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"id": 845,
|
| 330 |
+
"content": "<extra_id_19>",
|
| 331 |
+
"single_word": false,
|
| 332 |
+
"lstrip": false,
|
| 333 |
+
"rstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"special": true
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"id": 846,
|
| 339 |
+
"content": "<extra_id_20>",
|
| 340 |
+
"single_word": false,
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"rstrip": false,
|
| 343 |
+
"normalized": false,
|
| 344 |
+
"special": true
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"id": 847,
|
| 348 |
+
"content": "<extra_id_21>",
|
| 349 |
+
"single_word": false,
|
| 350 |
+
"lstrip": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"normalized": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"id": 848,
|
| 357 |
+
"content": "<extra_id_22>",
|
| 358 |
+
"single_word": false,
|
| 359 |
+
"lstrip": false,
|
| 360 |
+
"rstrip": false,
|
| 361 |
+
"normalized": false,
|
| 362 |
+
"special": true
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"id": 849,
|
| 366 |
+
"content": "<extra_id_23>",
|
| 367 |
+
"single_word": false,
|
| 368 |
+
"lstrip": false,
|
| 369 |
+
"rstrip": false,
|
| 370 |
+
"normalized": false,
|
| 371 |
+
"special": true
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"id": 850,
|
| 375 |
+
"content": "<extra_id_24>",
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"lstrip": false,
|
| 378 |
+
"rstrip": false,
|
| 379 |
+
"normalized": false,
|
| 380 |
+
"special": true
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"id": 851,
|
| 384 |
+
"content": "<extra_id_25>",
|
| 385 |
+
"single_word": false,
|
| 386 |
+
"lstrip": false,
|
| 387 |
+
"rstrip": false,
|
| 388 |
+
"normalized": false,
|
| 389 |
+
"special": true
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"id": 852,
|
| 393 |
+
"content": "<extra_id_26>",
|
| 394 |
+
"single_word": false,
|
| 395 |
+
"lstrip": false,
|
| 396 |
+
"rstrip": false,
|
| 397 |
+
"normalized": false,
|
| 398 |
+
"special": true
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"id": 853,
|
| 402 |
+
"content": "<extra_id_27>",
|
| 403 |
+
"single_word": false,
|
| 404 |
+
"lstrip": false,
|
| 405 |
+
"rstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"special": true
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"id": 854,
|
| 411 |
+
"content": "<extra_id_28>",
|
| 412 |
+
"single_word": false,
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"rstrip": false,
|
| 415 |
+
"normalized": false,
|
| 416 |
+
"special": true
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"id": 855,
|
| 420 |
+
"content": "<extra_id_29>",
|
| 421 |
+
"single_word": false,
|
| 422 |
+
"lstrip": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"normalized": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"id": 856,
|
| 429 |
+
"content": "<extra_id_30>",
|
| 430 |
+
"single_word": false,
|
| 431 |
+
"lstrip": false,
|
| 432 |
+
"rstrip": false,
|
| 433 |
+
"normalized": false,
|
| 434 |
+
"special": true
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"id": 857,
|
| 438 |
+
"content": "<extra_id_31>",
|
| 439 |
+
"single_word": false,
|
| 440 |
+
"lstrip": false,
|
| 441 |
+
"rstrip": false,
|
| 442 |
+
"normalized": false,
|
| 443 |
+
"special": true
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"id": 858,
|
| 447 |
+
"content": "<extra_id_32>",
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"lstrip": false,
|
| 450 |
+
"rstrip": false,
|
| 451 |
+
"normalized": false,
|
| 452 |
+
"special": true
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"id": 859,
|
| 456 |
+
"content": "<extra_id_33>",
|
| 457 |
+
"single_word": false,
|
| 458 |
+
"lstrip": false,
|
| 459 |
+
"rstrip": false,
|
| 460 |
+
"normalized": false,
|
| 461 |
+
"special": true
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"id": 860,
|
| 465 |
+
"content": "<extra_id_34>",
|
| 466 |
+
"single_word": false,
|
| 467 |
+
"lstrip": false,
|
| 468 |
+
"rstrip": false,
|
| 469 |
+
"normalized": false,
|
| 470 |
+
"special": true
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"id": 861,
|
| 474 |
+
"content": "<extra_id_35>",
|
| 475 |
+
"single_word": false,
|
| 476 |
+
"lstrip": false,
|
| 477 |
+
"rstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"special": true
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"id": 862,
|
| 483 |
+
"content": "<extra_id_36>",
|
| 484 |
+
"single_word": false,
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"rstrip": false,
|
| 487 |
+
"normalized": false,
|
| 488 |
+
"special": true
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"id": 863,
|
| 492 |
+
"content": "<extra_id_37>",
|
| 493 |
+
"single_word": false,
|
| 494 |
+
"lstrip": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"normalized": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"id": 864,
|
| 501 |
+
"content": "<extra_id_38>",
|
| 502 |
+
"single_word": false,
|
| 503 |
+
"lstrip": false,
|
| 504 |
+
"rstrip": false,
|
| 505 |
+
"normalized": false,
|
| 506 |
+
"special": true
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"id": 865,
|
| 510 |
+
"content": "<extra_id_39>",
|
| 511 |
+
"single_word": false,
|
| 512 |
+
"lstrip": false,
|
| 513 |
+
"rstrip": false,
|
| 514 |
+
"normalized": false,
|
| 515 |
+
"special": true
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"id": 866,
|
| 519 |
+
"content": "<extra_id_40>",
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"lstrip": false,
|
| 522 |
+
"rstrip": false,
|
| 523 |
+
"normalized": false,
|
| 524 |
+
"special": true
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"id": 867,
|
| 528 |
+
"content": "<extra_id_41>",
|
| 529 |
+
"single_word": false,
|
| 530 |
+
"lstrip": false,
|
| 531 |
+
"rstrip": false,
|
| 532 |
+
"normalized": false,
|
| 533 |
+
"special": true
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"id": 868,
|
| 537 |
+
"content": "<extra_id_42>",
|
| 538 |
+
"single_word": false,
|
| 539 |
+
"lstrip": false,
|
| 540 |
+
"rstrip": false,
|
| 541 |
+
"normalized": false,
|
| 542 |
+
"special": true
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"id": 869,
|
| 546 |
+
"content": "<extra_id_43>",
|
| 547 |
+
"single_word": false,
|
| 548 |
+
"lstrip": false,
|
| 549 |
+
"rstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"special": true
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"id": 870,
|
| 555 |
+
"content": "<extra_id_44>",
|
| 556 |
+
"single_word": false,
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"rstrip": false,
|
| 559 |
+
"normalized": false,
|
| 560 |
+
"special": true
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"id": 871,
|
| 564 |
+
"content": "<extra_id_45>",
|
| 565 |
+
"single_word": false,
|
| 566 |
+
"lstrip": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"normalized": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"id": 872,
|
| 573 |
+
"content": "<extra_id_46>",
|
| 574 |
+
"single_word": false,
|
| 575 |
+
"lstrip": false,
|
| 576 |
+
"rstrip": false,
|
| 577 |
+
"normalized": false,
|
| 578 |
+
"special": true
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"id": 873,
|
| 582 |
+
"content": "<extra_id_47>",
|
| 583 |
+
"single_word": false,
|
| 584 |
+
"lstrip": false,
|
| 585 |
+
"rstrip": false,
|
| 586 |
+
"normalized": false,
|
| 587 |
+
"special": true
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"id": 874,
|
| 591 |
+
"content": "<extra_id_48>",
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"lstrip": false,
|
| 594 |
+
"rstrip": false,
|
| 595 |
+
"normalized": false,
|
| 596 |
+
"special": true
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"id": 875,
|
| 600 |
+
"content": "<extra_id_49>",
|
| 601 |
+
"single_word": false,
|
| 602 |
+
"lstrip": false,
|
| 603 |
+
"rstrip": false,
|
| 604 |
+
"normalized": false,
|
| 605 |
+
"special": true
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"id": 876,
|
| 609 |
+
"content": "<extra_id_50>",
|
| 610 |
+
"single_word": false,
|
| 611 |
+
"lstrip": false,
|
| 612 |
+
"rstrip": false,
|
| 613 |
+
"normalized": false,
|
| 614 |
+
"special": true
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"id": 877,
|
| 618 |
+
"content": "<extra_id_51>",
|
| 619 |
+
"single_word": false,
|
| 620 |
+
"lstrip": false,
|
| 621 |
+
"rstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"special": true
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"id": 878,
|
| 627 |
+
"content": "<extra_id_52>",
|
| 628 |
+
"single_word": false,
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"rstrip": false,
|
| 631 |
+
"normalized": false,
|
| 632 |
+
"special": true
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"id": 879,
|
| 636 |
+
"content": "<extra_id_53>",
|
| 637 |
+
"single_word": false,
|
| 638 |
+
"lstrip": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"normalized": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"id": 880,
|
| 645 |
+
"content": "<extra_id_54>",
|
| 646 |
+
"single_word": false,
|
| 647 |
+
"lstrip": false,
|
| 648 |
+
"rstrip": false,
|
| 649 |
+
"normalized": false,
|
| 650 |
+
"special": true
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"id": 881,
|
| 654 |
+
"content": "<extra_id_55>",
|
| 655 |
+
"single_word": false,
|
| 656 |
+
"lstrip": false,
|
| 657 |
+
"rstrip": false,
|
| 658 |
+
"normalized": false,
|
| 659 |
+
"special": true
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"id": 882,
|
| 663 |
+
"content": "<extra_id_56>",
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"lstrip": false,
|
| 666 |
+
"rstrip": false,
|
| 667 |
+
"normalized": false,
|
| 668 |
+
"special": true
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"id": 883,
|
| 672 |
+
"content": "<extra_id_57>",
|
| 673 |
+
"single_word": false,
|
| 674 |
+
"lstrip": false,
|
| 675 |
+
"rstrip": false,
|
| 676 |
+
"normalized": false,
|
| 677 |
+
"special": true
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"id": 884,
|
| 681 |
+
"content": "<extra_id_58>",
|
| 682 |
+
"single_word": false,
|
| 683 |
+
"lstrip": false,
|
| 684 |
+
"rstrip": false,
|
| 685 |
+
"normalized": false,
|
| 686 |
+
"special": true
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"id": 885,
|
| 690 |
+
"content": "<extra_id_59>",
|
| 691 |
+
"single_word": false,
|
| 692 |
+
"lstrip": false,
|
| 693 |
+
"rstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"special": true
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"id": 886,
|
| 699 |
+
"content": "<extra_id_60>",
|
| 700 |
+
"single_word": false,
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"rstrip": false,
|
| 703 |
+
"normalized": false,
|
| 704 |
+
"special": true
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"id": 887,
|
| 708 |
+
"content": "<extra_id_61>",
|
| 709 |
+
"single_word": false,
|
| 710 |
+
"lstrip": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"normalized": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"id": 888,
|
| 717 |
+
"content": "<extra_id_62>",
|
| 718 |
+
"single_word": false,
|
| 719 |
+
"lstrip": false,
|
| 720 |
+
"rstrip": false,
|
| 721 |
+
"normalized": false,
|
| 722 |
+
"special": true
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"id": 889,
|
| 726 |
+
"content": "<extra_id_63>",
|
| 727 |
+
"single_word": false,
|
| 728 |
+
"lstrip": false,
|
| 729 |
+
"rstrip": false,
|
| 730 |
+
"normalized": false,
|
| 731 |
+
"special": true
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"id": 890,
|
| 735 |
+
"content": "<extra_id_64>",
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"lstrip": false,
|
| 738 |
+
"rstrip": false,
|
| 739 |
+
"normalized": false,
|
| 740 |
+
"special": true
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"id": 891,
|
| 744 |
+
"content": "<extra_id_65>",
|
| 745 |
+
"single_word": false,
|
| 746 |
+
"lstrip": false,
|
| 747 |
+
"rstrip": false,
|
| 748 |
+
"normalized": false,
|
| 749 |
+
"special": true
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"id": 892,
|
| 753 |
+
"content": "<extra_id_66>",
|
| 754 |
+
"single_word": false,
|
| 755 |
+
"lstrip": false,
|
| 756 |
+
"rstrip": false,
|
| 757 |
+
"normalized": false,
|
| 758 |
+
"special": true
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"id": 893,
|
| 762 |
+
"content": "<extra_id_67>",
|
| 763 |
+
"single_word": false,
|
| 764 |
+
"lstrip": false,
|
| 765 |
+
"rstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"special": true
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"id": 894,
|
| 771 |
+
"content": "<extra_id_68>",
|
| 772 |
+
"single_word": false,
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"rstrip": false,
|
| 775 |
+
"normalized": false,
|
| 776 |
+
"special": true
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"id": 895,
|
| 780 |
+
"content": "<extra_id_69>",
|
| 781 |
+
"single_word": false,
|
| 782 |
+
"lstrip": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"normalized": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"id": 896,
|
| 789 |
+
"content": "<extra_id_70>",
|
| 790 |
+
"single_word": false,
|
| 791 |
+
"lstrip": false,
|
| 792 |
+
"rstrip": false,
|
| 793 |
+
"normalized": false,
|
| 794 |
+
"special": true
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"id": 897,
|
| 798 |
+
"content": "<extra_id_71>",
|
| 799 |
+
"single_word": false,
|
| 800 |
+
"lstrip": false,
|
| 801 |
+
"rstrip": false,
|
| 802 |
+
"normalized": false,
|
| 803 |
+
"special": true
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"id": 898,
|
| 807 |
+
"content": "<extra_id_72>",
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"lstrip": false,
|
| 810 |
+
"rstrip": false,
|
| 811 |
+
"normalized": false,
|
| 812 |
+
"special": true
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"id": 899,
|
| 816 |
+
"content": "<extra_id_73>",
|
| 817 |
+
"single_word": false,
|
| 818 |
+
"lstrip": false,
|
| 819 |
+
"rstrip": false,
|
| 820 |
+
"normalized": false,
|
| 821 |
+
"special": true
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"id": 900,
|
| 825 |
+
"content": "<extra_id_74>",
|
| 826 |
+
"single_word": false,
|
| 827 |
+
"lstrip": false,
|
| 828 |
+
"rstrip": false,
|
| 829 |
+
"normalized": false,
|
| 830 |
+
"special": true
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"id": 901,
|
| 834 |
+
"content": "<extra_id_75>",
|
| 835 |
+
"single_word": false,
|
| 836 |
+
"lstrip": false,
|
| 837 |
+
"rstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"special": true
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"id": 902,
|
| 843 |
+
"content": "<extra_id_76>",
|
| 844 |
+
"single_word": false,
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"rstrip": false,
|
| 847 |
+
"normalized": false,
|
| 848 |
+
"special": true
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"id": 903,
|
| 852 |
+
"content": "<extra_id_77>",
|
| 853 |
+
"single_word": false,
|
| 854 |
+
"lstrip": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"normalized": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"id": 904,
|
| 861 |
+
"content": "<extra_id_78>",
|
| 862 |
+
"single_word": false,
|
| 863 |
+
"lstrip": false,
|
| 864 |
+
"rstrip": false,
|
| 865 |
+
"normalized": false,
|
| 866 |
+
"special": true
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"id": 905,
|
| 870 |
+
"content": "<extra_id_79>",
|
| 871 |
+
"single_word": false,
|
| 872 |
+
"lstrip": false,
|
| 873 |
+
"rstrip": false,
|
| 874 |
+
"normalized": false,
|
| 875 |
+
"special": true
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"id": 906,
|
| 879 |
+
"content": "<extra_id_80>",
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"lstrip": false,
|
| 882 |
+
"rstrip": false,
|
| 883 |
+
"normalized": false,
|
| 884 |
+
"special": true
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"id": 907,
|
| 888 |
+
"content": "<extra_id_81>",
|
| 889 |
+
"single_word": false,
|
| 890 |
+
"lstrip": false,
|
| 891 |
+
"rstrip": false,
|
| 892 |
+
"normalized": false,
|
| 893 |
+
"special": true
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"id": 908,
|
| 897 |
+
"content": "<extra_id_82>",
|
| 898 |
+
"single_word": false,
|
| 899 |
+
"lstrip": false,
|
| 900 |
+
"rstrip": false,
|
| 901 |
+
"normalized": false,
|
| 902 |
+
"special": true
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"id": 909,
|
| 906 |
+
"content": "<extra_id_83>",
|
| 907 |
+
"single_word": false,
|
| 908 |
+
"lstrip": false,
|
| 909 |
+
"rstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"special": true
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"id": 910,
|
| 915 |
+
"content": "<extra_id_84>",
|
| 916 |
+
"single_word": false,
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"rstrip": false,
|
| 919 |
+
"normalized": false,
|
| 920 |
+
"special": true
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"id": 911,
|
| 924 |
+
"content": "<extra_id_85>",
|
| 925 |
+
"single_word": false,
|
| 926 |
+
"lstrip": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"normalized": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"id": 912,
|
| 933 |
+
"content": "<extra_id_86>",
|
| 934 |
+
"single_word": false,
|
| 935 |
+
"lstrip": false,
|
| 936 |
+
"rstrip": false,
|
| 937 |
+
"normalized": false,
|
| 938 |
+
"special": true
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"id": 913,
|
| 942 |
+
"content": "<extra_id_87>",
|
| 943 |
+
"single_word": false,
|
| 944 |
+
"lstrip": false,
|
| 945 |
+
"rstrip": false,
|
| 946 |
+
"normalized": false,
|
| 947 |
+
"special": true
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"id": 914,
|
| 951 |
+
"content": "<extra_id_88>",
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"lstrip": false,
|
| 954 |
+
"rstrip": false,
|
| 955 |
+
"normalized": false,
|
| 956 |
+
"special": true
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"id": 915,
|
| 960 |
+
"content": "<extra_id_89>",
|
| 961 |
+
"single_word": false,
|
| 962 |
+
"lstrip": false,
|
| 963 |
+
"rstrip": false,
|
| 964 |
+
"normalized": false,
|
| 965 |
+
"special": true
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"id": 916,
|
| 969 |
+
"content": "<extra_id_90>",
|
| 970 |
+
"single_word": false,
|
| 971 |
+
"lstrip": false,
|
| 972 |
+
"rstrip": false,
|
| 973 |
+
"normalized": false,
|
| 974 |
+
"special": true
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"id": 917,
|
| 978 |
+
"content": "<extra_id_91>",
|
| 979 |
+
"single_word": false,
|
| 980 |
+
"lstrip": false,
|
| 981 |
+
"rstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"special": true
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"id": 918,
|
| 987 |
+
"content": "<extra_id_92>",
|
| 988 |
+
"single_word": false,
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"rstrip": false,
|
| 991 |
+
"normalized": false,
|
| 992 |
+
"special": true
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"id": 919,
|
| 996 |
+
"content": "<extra_id_93>",
|
| 997 |
+
"single_word": false,
|
| 998 |
+
"lstrip": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"normalized": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"id": 920,
|
| 1005 |
+
"content": "<extra_id_94>",
|
| 1006 |
+
"single_word": false,
|
| 1007 |
+
"lstrip": false,
|
| 1008 |
+
"rstrip": false,
|
| 1009 |
+
"normalized": false,
|
| 1010 |
+
"special": true
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"id": 921,
|
| 1014 |
+
"content": "<extra_id_95>",
|
| 1015 |
+
"single_word": false,
|
| 1016 |
+
"lstrip": false,
|
| 1017 |
+
"rstrip": false,
|
| 1018 |
+
"normalized": false,
|
| 1019 |
+
"special": true
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"id": 922,
|
| 1023 |
+
"content": "<extra_id_96>",
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"lstrip": false,
|
| 1026 |
+
"rstrip": false,
|
| 1027 |
+
"normalized": false,
|
| 1028 |
+
"special": true
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"id": 923,
|
| 1032 |
+
"content": "<extra_id_97>",
|
| 1033 |
+
"single_word": false,
|
| 1034 |
+
"lstrip": false,
|
| 1035 |
+
"rstrip": false,
|
| 1036 |
+
"normalized": false,
|
| 1037 |
+
"special": true
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"id": 924,
|
| 1041 |
+
"content": "<extra_id_98>",
|
| 1042 |
+
"single_word": false,
|
| 1043 |
+
"lstrip": false,
|
| 1044 |
+
"rstrip": false,
|
| 1045 |
+
"normalized": false,
|
| 1046 |
+
"special": true
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"id": 925,
|
| 1050 |
+
"content": "<extra_id_99>",
|
| 1051 |
+
"single_word": false,
|
| 1052 |
+
"lstrip": false,
|
| 1053 |
+
"rstrip": false,
|
| 1054 |
+
"normalized": false,
|
| 1055 |
+
"special": true
|
| 1056 |
+
}
|
| 1057 |
+
],
|
| 1058 |
+
"normalizer": {
|
| 1059 |
+
"type": "NFKC"
|
| 1060 |
+
},
|
| 1061 |
+
"pre_tokenizer": {
|
| 1062 |
+
"type": "Metaspace",
|
| 1063 |
+
"replacement": "▁",
|
| 1064 |
+
"prepend_scheme": "never",
|
| 1065 |
+
"split": true
|
| 1066 |
+
},
|
| 1067 |
+
"post_processor": null,
|
| 1068 |
+
"decoder": {
|
| 1069 |
+
"type": "Metaspace",
|
| 1070 |
+
"replacement": "▁",
|
| 1071 |
+
"prepend_scheme": "never",
|
| 1072 |
+
"split": true
|
| 1073 |
+
},
|
| 1074 |
+
"model": {
|
| 1075 |
+
"type": "BPE",
|
| 1076 |
+
"dropout": null,
|
| 1077 |
+
"unk_token": "<unk>",
|
| 1078 |
+
"continuing_subword_prefix": null,
|
| 1079 |
+
"end_of_word_suffix": null,
|
| 1080 |
+
"fuse_unk": false,
|
| 1081 |
+
"byte_fallback": false,
|
| 1082 |
+
"ignore_merges": false,
|
| 1083 |
+
"vocab": {
|
| 1084 |
+
"<unk>": 0,
|
| 1085 |
+
"0": 1,
|
| 1086 |
+
"1": 2,
|
| 1087 |
+
"2": 3,
|
| 1088 |
+
"3": 4,
|
| 1089 |
+
"4": 5,
|
| 1090 |
+
"5": 6,
|
| 1091 |
+
"6": 7,
|
| 1092 |
+
"7": 8,
|
| 1093 |
+
"8": 9,
|
| 1094 |
+
"9": 10,
|
| 1095 |
+
"<": 11,
|
| 1096 |
+
">": 12,
|
| 1097 |
+
"a": 13,
|
| 1098 |
+
"b": 14,
|
| 1099 |
+
"c": 15,
|
| 1100 |
+
"d": 16,
|
| 1101 |
+
"e": 17,
|
| 1102 |
+
"f": 18,
|
| 1103 |
+
"g": 19,
|
| 1104 |
+
"h": 20,
|
| 1105 |
+
"i": 21,
|
| 1106 |
+
"j": 22,
|
| 1107 |
+
"k": 23,
|
| 1108 |
+
"l": 24,
|
| 1109 |
+
"m": 25,
|
| 1110 |
+
"n": 26,
|
| 1111 |
+
"o": 27,
|
| 1112 |
+
"p": 28,
|
| 1113 |
+
"q": 29,
|
| 1114 |
+
"r": 30,
|
| 1115 |
+
"s": 31,
|
| 1116 |
+
"t": 32,
|
| 1117 |
+
"u": 33,
|
| 1118 |
+
"v": 34,
|
| 1119 |
+
"w": 35,
|
| 1120 |
+
"x": 36,
|
| 1121 |
+
"y": 37,
|
| 1122 |
+
"z": 38,
|
| 1123 |
+
"á": 39,
|
| 1124 |
+
"è": 40,
|
| 1125 |
+
"é": 41,
|
| 1126 |
+
"": 42,
|
| 1127 |
+
"،": 43,
|
| 1128 |
+
"ؐ": 44,
|
| 1129 |
+
"ؑ": 45,
|
| 1130 |
+
"ؓ": 46,
|
| 1131 |
+
"ء": 47,
|
| 1132 |
+
"آ": 48,
|
| 1133 |
+
"ؤ": 49,
|
| 1134 |
+
"ئ": 50,
|
| 1135 |
+
"ا": 51,
|
| 1136 |
+
"ب": 52,
|
| 1137 |
+
"ة": 53,
|
| 1138 |
+
"ت": 54,
|
| 1139 |
+
"ث": 55,
|
| 1140 |
+
"ج": 56,
|
| 1141 |
+
"ح": 57,
|
| 1142 |
+
"خ": 58,
|
| 1143 |
+
"د": 59,
|
| 1144 |
+
"ذ": 60,
|
| 1145 |
+
"ر": 61,
|
| 1146 |
+
"ز": 62,
|
| 1147 |
+
"س": 63,
|
| 1148 |
+
"ش": 64,
|
| 1149 |
+
"ص": 65,
|
| 1150 |
+
"ض": 66,
|
| 1151 |
+
"ط": 67,
|
| 1152 |
+
"ظ": 68,
|
| 1153 |
+
"ع": 69,
|
| 1154 |
+
"غ": 70,
|
| 1155 |
+
"ـ": 71,
|
| 1156 |
+
"ف": 72,
|
| 1157 |
+
"ق": 73,
|
| 1158 |
+
"ك": 74,
|
| 1159 |
+
"ل": 75,
|
| 1160 |
+
"م": 76,
|
| 1161 |
+
"ن": 77,
|
| 1162 |
+
"ه": 78,
|
| 1163 |
+
"و": 79,
|
| 1164 |
+
"ي": 80,
|
| 1165 |
+
"ً": 81,
|
| 1166 |
+
"ٌ": 82,
|
| 1167 |
+
"َ": 83,
|
| 1168 |
+
"ُ": 84,
|
| 1169 |
+
"ِ": 85,
|
| 1170 |
+
"ّ": 86,
|
| 1171 |
+
"ٓ": 87,
|
| 1172 |
+
"ٔ": 88,
|
| 1173 |
+
"ٕ": 89,
|
| 1174 |
+
"ٖ": 90,
|
| 1175 |
+
"ٗ": 91,
|
| 1176 |
+
"٘": 92,
|
| 1177 |
+
"ٚ": 93,
|
| 1178 |
+
"ٛ": 94,
|
| 1179 |
+
"٠": 95,
|
| 1180 |
+
"١": 96,
|
| 1181 |
+
"٢": 97,
|
| 1182 |
+
"٣": 98,
|
| 1183 |
+
"٤": 99,
|
| 1184 |
+
"٥": 100,
|
| 1185 |
+
"٦": 101,
|
| 1186 |
+
"٧": 102,
|
| 1187 |
+
"٨": 103,
|
| 1188 |
+
"٩": 104,
|
| 1189 |
+
"ٮ": 105,
|
| 1190 |
+
"ٰ": 106,
|
| 1191 |
+
"ٲ": 107,
|
| 1192 |
+
"ٴ": 108,
|
| 1193 |
+
"ٹ": 109,
|
| 1194 |
+
"ٺ": 110,
|
| 1195 |
+
"ٻ": 111,
|
| 1196 |
+
"ٽ": 112,
|
| 1197 |
+
"پ": 113,
|
| 1198 |
+
"ٿ": 114,
|
| 1199 |
+
"ڀ": 115,
|
| 1200 |
+
"ڃ": 116,
|
| 1201 |
+
"ڄ": 117,
|
| 1202 |
+
"چ": 118,
|
| 1203 |
+
"ڇ": 119,
|
| 1204 |
+
"ڈ": 120,
|
| 1205 |
+
"ڊ": 121,
|
| 1206 |
+
"ڌ": 122,
|
| 1207 |
+
"ڍ": 123,
|
| 1208 |
+
"ڏ": 124,
|
| 1209 |
+
"ڑ": 125,
|
| 1210 |
+
"ژ": 126,
|
| 1211 |
+
"ڙ": 127,
|
| 1212 |
+
"ڦ": 128,
|
| 1213 |
+
"ک": 129,
|
| 1214 |
+
"ڪ": 130,
|
| 1215 |
+
"گ": 131,
|
| 1216 |
+
"ڱ": 132,
|
| 1217 |
+
"ڳ": 133,
|
| 1218 |
+
"ں": 134,
|
| 1219 |
+
"ڻ": 135,
|
| 1220 |
+
"ھ": 136,
|
| 1221 |
+
"ہ": 137,
|
| 1222 |
+
"ۂ": 138,
|
| 1223 |
+
"ۃ": 139,
|
| 1224 |
+
"ۄ": 140,
|
| 1225 |
+
"ی": 141,
|
| 1226 |
+
"ۍ": 142,
|
| 1227 |
+
"ے": 143,
|
| 1228 |
+
"ۓ": 144,
|
| 1229 |
+
"۪": 145,
|
| 1230 |
+
"ۭ": 146,
|
| 1231 |
+
"۶": 147,
|
| 1232 |
+
"۾": 148,
|
| 1233 |
+
"ँ": 149,
|
| 1234 |
+
"ं": 150,
|
| 1235 |
+
"ः": 151,
|
| 1236 |
+
"अ": 152,
|
| 1237 |
+
"आ": 153,
|
| 1238 |
+
"इ": 154,
|
| 1239 |
+
"ई": 155,
|
| 1240 |
+
"उ": 156,
|
| 1241 |
+
"ऊ": 157,
|
| 1242 |
+
"ऋ": 158,
|
| 1243 |
+
"ऌ": 159,
|
| 1244 |
+
"ऍ": 160,
|
| 1245 |
+
"ए": 161,
|
| 1246 |
+
"ऐ": 162,
|
| 1247 |
+
"ऑ": 163,
|
| 1248 |
+
"ओ": 164,
|
| 1249 |
+
"औ": 165,
|
| 1250 |
+
"क": 166,
|
| 1251 |
+
"ख": 167,
|
| 1252 |
+
"ग": 168,
|
| 1253 |
+
"घ": 169,
|
| 1254 |
+
"ङ": 170,
|
| 1255 |
+
"च": 171,
|
| 1256 |
+
"छ": 172,
|
| 1257 |
+
"ज": 173,
|
| 1258 |
+
"झ": 174,
|
| 1259 |
+
"ञ": 175,
|
| 1260 |
+
"ट": 176,
|
| 1261 |
+
"ठ": 177,
|
| 1262 |
+
"ड": 178,
|
| 1263 |
+
"ढ": 179,
|
| 1264 |
+
"ण": 180,
|
| 1265 |
+
"त": 181,
|
| 1266 |
+
"थ": 182,
|
| 1267 |
+
"द": 183,
|
| 1268 |
+
"ध": 184,
|
| 1269 |
+
"न": 185,
|
| 1270 |
+
"प": 186,
|
| 1271 |
+
"फ": 187,
|
| 1272 |
+
"ब": 188,
|
| 1273 |
+
"भ": 189,
|
| 1274 |
+
"म": 190,
|
| 1275 |
+
"य": 191,
|
| 1276 |
+
"र": 192,
|
| 1277 |
+
"ऱ": 193,
|
| 1278 |
+
"ल": 194,
|
| 1279 |
+
"ळ": 195,
|
| 1280 |
+
"व": 196,
|
| 1281 |
+
"श": 197,
|
| 1282 |
+
"ष": 198,
|
| 1283 |
+
"स": 199,
|
| 1284 |
+
"ह": 200,
|
| 1285 |
+
"़": 201,
|
| 1286 |
+
"ऽ": 202,
|
| 1287 |
+
"ा": 203,
|
| 1288 |
+
"ि": 204,
|
| 1289 |
+
"ी": 205,
|
| 1290 |
+
"ु": 206,
|
| 1291 |
+
"ू": 207,
|
| 1292 |
+
"ृ": 208,
|
| 1293 |
+
"ॅ": 209,
|
| 1294 |
+
"ॆ": 210,
|
| 1295 |
+
"े": 211,
|
| 1296 |
+
"ै": 212,
|
| 1297 |
+
"ॉ": 213,
|
| 1298 |
+
"ॊ": 214,
|
| 1299 |
+
"ो": 215,
|
| 1300 |
+
"ौ": 216,
|
| 1301 |
+
"्": 217,
|
| 1302 |
+
"ॐ": 218,
|
| 1303 |
+
"ॠ": 219,
|
| 1304 |
+
"।": 220,
|
| 1305 |
+
"॥": 221,
|
| 1306 |
+
"०": 222,
|
| 1307 |
+
"१": 223,
|
| 1308 |
+
"२": 224,
|
| 1309 |
+
"३": 225,
|
| 1310 |
+
"४": 226,
|
| 1311 |
+
"५": 227,
|
| 1312 |
+
"६": 228,
|
| 1313 |
+
"७": 229,
|
| 1314 |
+
"८": 230,
|
| 1315 |
+
"९": 231,
|
| 1316 |
+
"॰": 232,
|
| 1317 |
+
"ঁ": 233,
|
| 1318 |
+
"ং": 234,
|
| 1319 |
+
"ঃ": 235,
|
| 1320 |
+
"অ": 236,
|
| 1321 |
+
"আ": 237,
|
| 1322 |
+
"ই": 238,
|
| 1323 |
+
"ঈ": 239,
|
| 1324 |
+
"উ": 240,
|
| 1325 |
+
"ঊ": 241,
|
| 1326 |
+
"ঋ": 242,
|
| 1327 |
+
"এ": 243,
|
| 1328 |
+
"ঐ": 244,
|
| 1329 |
+
"ও": 245,
|
| 1330 |
+
"ঔ": 246,
|
| 1331 |
+
"ক": 247,
|
| 1332 |
+
"খ": 248,
|
| 1333 |
+
"গ": 249,
|
| 1334 |
+
"ঘ": 250,
|
| 1335 |
+
"ঙ": 251,
|
| 1336 |
+
"চ": 252,
|
| 1337 |
+
"ছ": 253,
|
| 1338 |
+
"জ": 254,
|
| 1339 |
+
"ঝ": 255,
|
| 1340 |
+
"ঞ": 256,
|
| 1341 |
+
"ট": 257,
|
| 1342 |
+
"ঠ": 258,
|
| 1343 |
+
"ড": 259,
|
| 1344 |
+
"ঢ": 260,
|
| 1345 |
+
"ণ": 261,
|
| 1346 |
+
"ত": 262,
|
| 1347 |
+
"থ": 263,
|
| 1348 |
+
"দ": 264,
|
| 1349 |
+
"ধ": 265,
|
| 1350 |
+
"ন": 266,
|
| 1351 |
+
"প": 267,
|
| 1352 |
+
"ফ": 268,
|
| 1353 |
+
"ব": 269,
|
| 1354 |
+
"ভ": 270,
|
| 1355 |
+
"ম": 271,
|
| 1356 |
+
"য": 272,
|
| 1357 |
+
"র": 273,
|
| 1358 |
+
"ল": 274,
|
| 1359 |
+
"শ": 275,
|
| 1360 |
+
"ষ": 276,
|
| 1361 |
+
"স": 277,
|
| 1362 |
+
"হ": 278,
|
| 1363 |
+
"়": 279,
|
| 1364 |
+
"া": 280,
|
| 1365 |
+
"ি": 281,
|
| 1366 |
+
"ী": 282,
|
| 1367 |
+
"ু": 283,
|
| 1368 |
+
"ূ": 284,
|
| 1369 |
+
"ৃ": 285,
|
| 1370 |
+
"ে": 286,
|
| 1371 |
+
"ৈ": 287,
|
| 1372 |
+
"ো": 288,
|
| 1373 |
+
"ৌ": 289,
|
| 1374 |
+
"্": 290,
|
| 1375 |
+
"ৎ": 291,
|
| 1376 |
+
"০": 292,
|
| 1377 |
+
"১": 293,
|
| 1378 |
+
"২": 294,
|
| 1379 |
+
"৩": 295,
|
| 1380 |
+
"৪": 296,
|
| 1381 |
+
"৫": 297,
|
| 1382 |
+
"৬": 298,
|
| 1383 |
+
"৭": 299,
|
| 1384 |
+
"৮": 300,
|
| 1385 |
+
"৯": 301,
|
| 1386 |
+
"ৰ": 302,
|
| 1387 |
+
"ৱ": 303,
|
| 1388 |
+
"ਂ": 304,
|
| 1389 |
+
"ਃ": 305,
|
| 1390 |
+
"ਅ": 306,
|
| 1391 |
+
"ਆ": 307,
|
| 1392 |
+
"ਇ": 308,
|
| 1393 |
+
"ਈ": 309,
|
| 1394 |
+
"ਉ": 310,
|
| 1395 |
+
"ਊ": 311,
|
| 1396 |
+
"ਏ": 312,
|
| 1397 |
+
"ਐ": 313,
|
| 1398 |
+
"ਓ": 314,
|
| 1399 |
+
"ਔ": 315,
|
| 1400 |
+
"ਕ": 316,
|
| 1401 |
+
"ਖ": 317,
|
| 1402 |
+
"ਗ": 318,
|
| 1403 |
+
"ਘ": 319,
|
| 1404 |
+
"ਙ": 320,
|
| 1405 |
+
"ਚ": 321,
|
| 1406 |
+
"ਛ": 322,
|
| 1407 |
+
"ਜ": 323,
|
| 1408 |
+
"ਝ": 324,
|
| 1409 |
+
"ਞ": 325,
|
| 1410 |
+
"ਟ": 326,
|
| 1411 |
+
"ਠ": 327,
|
| 1412 |
+
"ਡ": 328,
|
| 1413 |
+
"ਢ": 329,
|
| 1414 |
+
"ਣ": 330,
|
| 1415 |
+
"ਤ": 331,
|
| 1416 |
+
"ਥ": 332,
|
| 1417 |
+
"ਦ": 333,
|
| 1418 |
+
"ਧ": 334,
|
| 1419 |
+
"ਨ": 335,
|
| 1420 |
+
"ਪ": 336,
|
| 1421 |
+
"ਫ": 337,
|
| 1422 |
+
"ਬ": 338,
|
| 1423 |
+
"ਭ": 339,
|
| 1424 |
+
"ਮ": 340,
|
| 1425 |
+
"ਯ": 341,
|
| 1426 |
+
"ਰ": 342,
|
| 1427 |
+
"ਲ": 343,
|
| 1428 |
+
"ਵ": 344,
|
| 1429 |
+
"ਸ": 345,
|
| 1430 |
+
"ਹ": 346,
|
| 1431 |
+
"਼": 347,
|
| 1432 |
+
"ਾ": 348,
|
| 1433 |
+
"ਿ": 349,
|
| 1434 |
+
"ੀ": 350,
|
| 1435 |
+
"ੁ": 351,
|
| 1436 |
+
"ੂ": 352,
|
| 1437 |
+
"ੇ": 353,
|
| 1438 |
+
"ੈ": 354,
|
| 1439 |
+
"ੋ": 355,
|
| 1440 |
+
"ੌ": 356,
|
| 1441 |
+
"੍": 357,
|
| 1442 |
+
"ੜ": 358,
|
| 1443 |
+
"੦": 359,
|
| 1444 |
+
"੧": 360,
|
| 1445 |
+
"੨": 361,
|
| 1446 |
+
"੩": 362,
|
| 1447 |
+
"੪": 363,
|
| 1448 |
+
"੫": 364,
|
| 1449 |
+
"੬": 365,
|
| 1450 |
+
"੭": 366,
|
| 1451 |
+
"੮": 367,
|
| 1452 |
+
"੯": 368,
|
| 1453 |
+
"ੰ": 369,
|
| 1454 |
+
"ੱ": 370,
|
| 1455 |
+
"ੲ": 371,
|
| 1456 |
+
"ੳ": 372,
|
| 1457 |
+
"ઁ": 373,
|
| 1458 |
+
"ં": 374,
|
| 1459 |
+
"ઃ": 375,
|
| 1460 |
+
"અ": 376,
|
| 1461 |
+
"આ": 377,
|
| 1462 |
+
"ઇ": 378,
|
| 1463 |
+
"ઈ": 379,
|
| 1464 |
+
"ઉ": 380,
|
| 1465 |
+
"ઊ": 381,
|
| 1466 |
+
"ઋ": 382,
|
| 1467 |
+
"ઍ": 383,
|
| 1468 |
+
"એ": 384,
|
| 1469 |
+
"ઐ": 385,
|
| 1470 |
+
"ઑ": 386,
|
| 1471 |
+
"ઓ": 387,
|
| 1472 |
+
"ઔ": 388,
|
| 1473 |
+
"ક": 389,
|
| 1474 |
+
"ખ": 390,
|
| 1475 |
+
"ગ": 391,
|
| 1476 |
+
"ઘ": 392,
|
| 1477 |
+
"ઙ": 393,
|
| 1478 |
+
"ચ": 394,
|
| 1479 |
+
"છ": 395,
|
| 1480 |
+
"જ": 396,
|
| 1481 |
+
"ઝ": 397,
|
| 1482 |
+
"ઞ": 398,
|
| 1483 |
+
"ટ": 399,
|
| 1484 |
+
"ઠ": 400,
|
| 1485 |
+
"ડ": 401,
|
| 1486 |
+
"ઢ": 402,
|
| 1487 |
+
"ણ": 403,
|
| 1488 |
+
"ત": 404,
|
| 1489 |
+
"થ": 405,
|
| 1490 |
+
"દ": 406,
|
| 1491 |
+
"ધ": 407,
|
| 1492 |
+
"ન": 408,
|
| 1493 |
+
"પ": 409,
|
| 1494 |
+
"ફ": 410,
|
| 1495 |
+
"બ": 411,
|
| 1496 |
+
"ભ": 412,
|
| 1497 |
+
"મ": 413,
|
| 1498 |
+
"ય": 414,
|
| 1499 |
+
"ર": 415,
|
| 1500 |
+
"લ": 416,
|
| 1501 |
+
"ળ": 417,
|
| 1502 |
+
"વ": 418,
|
| 1503 |
+
"શ": 419,
|
| 1504 |
+
"ષ": 420,
|
| 1505 |
+
"સ": 421,
|
| 1506 |
+
"હ": 422,
|
| 1507 |
+
"઼": 423,
|
| 1508 |
+
"ા": 424,
|
| 1509 |
+
"િ": 425,
|
| 1510 |
+
"ી": 426,
|
| 1511 |
+
"ુ": 427,
|
| 1512 |
+
"ૂ": 428,
|
| 1513 |
+
"ૃ": 429,
|
| 1514 |
+
"ૅ": 430,
|
| 1515 |
+
"ે": 431,
|
| 1516 |
+
"ૈ": 432,
|
| 1517 |
+
"ૉ": 433,
|
| 1518 |
+
"ો": 434,
|
| 1519 |
+
"ૌ": 435,
|
| 1520 |
+
"્": 436,
|
| 1521 |
+
"ૐ": 437,
|
| 1522 |
+
"ૠ": 438,
|
| 1523 |
+
"૦": 439,
|
| 1524 |
+
"૧": 440,
|
| 1525 |
+
"૨": 441,
|
| 1526 |
+
"૩": 442,
|
| 1527 |
+
"૪": 443,
|
| 1528 |
+
"૫": 444,
|
| 1529 |
+
"૬": 445,
|
| 1530 |
+
"૭": 446,
|
| 1531 |
+
"૮": 447,
|
| 1532 |
+
"૯": 448,
|
| 1533 |
+
"૰": 449,
|
| 1534 |
+
"ଁ": 450,
|
| 1535 |
+
"ଂ": 451,
|
| 1536 |
+
"ଃ": 452,
|
| 1537 |
+
"ଅ": 453,
|
| 1538 |
+
"ଆ": 454,
|
| 1539 |
+
"ଇ": 455,
|
| 1540 |
+
"ଈ": 456,
|
| 1541 |
+
"ଉ": 457,
|
| 1542 |
+
"ଊ": 458,
|
| 1543 |
+
"ଋ": 459,
|
| 1544 |
+
"ଏ": 460,
|
| 1545 |
+
"ଐ": 461,
|
| 1546 |
+
"ଓ": 462,
|
| 1547 |
+
"ଔ": 463,
|
| 1548 |
+
"କ": 464,
|
| 1549 |
+
"ଖ": 465,
|
| 1550 |
+
"ଗ": 466,
|
| 1551 |
+
"ଘ": 467,
|
| 1552 |
+
"ଙ": 468,
|
| 1553 |
+
"ଚ": 469,
|
| 1554 |
+
"ଛ": 470,
|
| 1555 |
+
"ଜ": 471,
|
| 1556 |
+
"ଝ": 472,
|
| 1557 |
+
"ଞ": 473,
|
| 1558 |
+
"ଟ": 474,
|
| 1559 |
+
"ଠ": 475,
|
| 1560 |
+
"ଡ": 476,
|
| 1561 |
+
"ଢ": 477,
|
| 1562 |
+
"ଣ": 478,
|
| 1563 |
+
"ତ": 479,
|
| 1564 |
+
"ଥ": 480,
|
| 1565 |
+
"ଦ": 481,
|
| 1566 |
+
"ଧ": 482,
|
| 1567 |
+
"ନ": 483,
|
| 1568 |
+
"ପ": 484,
|
| 1569 |
+
"ଫ": 485,
|
| 1570 |
+
"ବ": 486,
|
| 1571 |
+
"ଭ": 487,
|
| 1572 |
+
"ମ": 488,
|
| 1573 |
+
"ଯ": 489,
|
| 1574 |
+
"ର": 490,
|
| 1575 |
+
"ଲ": 491,
|
| 1576 |
+
"ଳ": 492,
|
| 1577 |
+
"ଶ": 493,
|
| 1578 |
+
"ଷ": 494,
|
| 1579 |
+
"ସ": 495,
|
| 1580 |
+
"ହ": 496,
|
| 1581 |
+
"଼": 497,
|
| 1582 |
+
"ା": 498,
|
| 1583 |
+
"ି": 499,
|
| 1584 |
+
"ୀ": 500,
|
| 1585 |
+
"ୁ": 501,
|
| 1586 |
+
"ୂ": 502,
|
| 1587 |
+
"ୃ": 503,
|
| 1588 |
+
"େ": 504,
|
| 1589 |
+
"ୈ": 505,
|
| 1590 |
+
"ୋ": 506,
|
| 1591 |
+
"ୌ": 507,
|
| 1592 |
+
"୍": 508,
|
| 1593 |
+
"": 509,
|
| 1594 |
+
"ୟ": 510,
|
| 1595 |
+
"ୢ": 511,
|
| 1596 |
+
"୦": 512,
|
| 1597 |
+
"୧": 513,
|
| 1598 |
+
"୨": 514,
|
| 1599 |
+
"୩": 515,
|
| 1600 |
+
"୪": 516,
|
| 1601 |
+
"୫": 517,
|
| 1602 |
+
"୬": 518,
|
| 1603 |
+
"୭": 519,
|
| 1604 |
+
"୮": 520,
|
| 1605 |
+
"୯": 521,
|
| 1606 |
+
"ୱ": 522,
|
| 1607 |
+
"ஂ": 523,
|
| 1608 |
+
"ஃ": 524,
|
| 1609 |
+
"அ": 525,
|
| 1610 |
+
"ஆ": 526,
|
| 1611 |
+
"இ": 527,
|
| 1612 |
+
"ஈ": 528,
|
| 1613 |
+
"உ": 529,
|
| 1614 |
+
"ஊ": 530,
|
| 1615 |
+
"எ": 531,
|
| 1616 |
+
"ஏ": 532,
|
| 1617 |
+
"ஐ": 533,
|
| 1618 |
+
"ஒ": 534,
|
| 1619 |
+
"ஓ": 535,
|
| 1620 |
+
"ஔ": 536,
|
| 1621 |
+
"க": 537,
|
| 1622 |
+
"ங": 538,
|
| 1623 |
+
"ச": 539,
|
| 1624 |
+
"ஜ": 540,
|
| 1625 |
+
"ஞ": 541,
|
| 1626 |
+
"ட": 542,
|
| 1627 |
+
"ண": 543,
|
| 1628 |
+
"த": 544,
|
| 1629 |
+
"ந": 545,
|
| 1630 |
+
"ன": 546,
|
| 1631 |
+
"ப": 547,
|
| 1632 |
+
"ம": 548,
|
| 1633 |
+
"ய": 549,
|
| 1634 |
+
"ர": 550,
|
| 1635 |
+
"ற": 551,
|
| 1636 |
+
"ல": 552,
|
| 1637 |
+
"ள": 553,
|
| 1638 |
+
"ழ": 554,
|
| 1639 |
+
"வ": 555,
|
| 1640 |
+
"ஷ": 556,
|
| 1641 |
+
"ஸ": 557,
|
| 1642 |
+
"ஹ": 558,
|
| 1643 |
+
"ா": 559,
|
| 1644 |
+
"ி": 560,
|
| 1645 |
+
"ீ": 561,
|
| 1646 |
+
"ு": 562,
|
| 1647 |
+
"ூ": 563,
|
| 1648 |
+
"ெ": 564,
|
| 1649 |
+
"ே": 565,
|
| 1650 |
+
"ை": 566,
|
| 1651 |
+
"ொ": 567,
|
| 1652 |
+
"ோ": 568,
|
| 1653 |
+
"ௌ": 569,
|
| 1654 |
+
"்": 570,
|
| 1655 |
+
"௦": 571,
|
| 1656 |
+
"௧": 572,
|
| 1657 |
+
"௨": 573,
|
| 1658 |
+
"௩": 574,
|
| 1659 |
+
"௪": 575,
|
| 1660 |
+
"௫": 576,
|
| 1661 |
+
"௬": 577,
|
| 1662 |
+
"௭": 578,
|
| 1663 |
+
"௮": 579,
|
| 1664 |
+
"௯": 580,
|
| 1665 |
+
"ఁ": 581,
|
| 1666 |
+
"ం": 582,
|
| 1667 |
+
"ః": 583,
|
| 1668 |
+
"అ": 584,
|
| 1669 |
+
"ఆ": 585,
|
| 1670 |
+
"ఇ": 586,
|
| 1671 |
+
"ఈ": 587,
|
| 1672 |
+
"ఉ": 588,
|
| 1673 |
+
"ఊ": 589,
|
| 1674 |
+
"ఋ": 590,
|
| 1675 |
+
"ఎ": 591,
|
| 1676 |
+
"ఏ": 592,
|
| 1677 |
+
"ఐ": 593,
|
| 1678 |
+
"ఒ": 594,
|
| 1679 |
+
"ఓ": 595,
|
| 1680 |
+
"ఔ": 596,
|
| 1681 |
+
"క": 597,
|
| 1682 |
+
"ఖ": 598,
|
| 1683 |
+
"గ": 599,
|
| 1684 |
+
"ఘ": 600,
|
| 1685 |
+
"ఙ": 601,
|
| 1686 |
+
"చ": 602,
|
| 1687 |
+
"ఛ": 603,
|
| 1688 |
+
"జ": 604,
|
| 1689 |
+
"ఝ": 605,
|
| 1690 |
+
"ఞ": 606,
|
| 1691 |
+
"ట": 607,
|
| 1692 |
+
"ఠ": 608,
|
| 1693 |
+
"డ": 609,
|
| 1694 |
+
"ఢ": 610,
|
| 1695 |
+
"ణ": 611,
|
| 1696 |
+
"త": 612,
|
| 1697 |
+
"థ": 613,
|
| 1698 |
+
"ద": 614,
|
| 1699 |
+
"ధ": 615,
|
| 1700 |
+
"న": 616,
|
| 1701 |
+
"ప": 617,
|
| 1702 |
+
"ఫ": 618,
|
| 1703 |
+
"బ": 619,
|
| 1704 |
+
"భ": 620,
|
| 1705 |
+
"మ": 621,
|
| 1706 |
+
"య": 622,
|
| 1707 |
+
"ర": 623,
|
| 1708 |
+
"ఱ": 624,
|
| 1709 |
+
"ల": 625,
|
| 1710 |
+
"ళ": 626,
|
| 1711 |
+
"వ": 627,
|
| 1712 |
+
"శ": 628,
|
| 1713 |
+
"ష": 629,
|
| 1714 |
+
"స": 630,
|
| 1715 |
+
"హ": 631,
|
| 1716 |
+
"ా": 632,
|
| 1717 |
+
"ి": 633,
|
| 1718 |
+
"ీ": 634,
|
| 1719 |
+
"ు": 635,
|
| 1720 |
+
"ూ": 636,
|
| 1721 |
+
"ృ": 637,
|
| 1722 |
+
"ౄ": 638,
|
| 1723 |
+
"ె": 639,
|
| 1724 |
+
"ే": 640,
|
| 1725 |
+
"ై": 641,
|
| 1726 |
+
"ొ": 642,
|
| 1727 |
+
"ో": 643,
|
| 1728 |
+
"ౌ": 644,
|
| 1729 |
+
"్": 645,
|
| 1730 |
+
"౦": 646,
|
| 1731 |
+
"౧": 647,
|
| 1732 |
+
"౨": 648,
|
| 1733 |
+
"౩": 649,
|
| 1734 |
+
"౪": 650,
|
| 1735 |
+
"౫": 651,
|
| 1736 |
+
"౬": 652,
|
| 1737 |
+
"౭": 653,
|
| 1738 |
+
"౮": 654,
|
| 1739 |
+
"౯": 655,
|
| 1740 |
+
"ಂ": 656,
|
| 1741 |
+
"ಃ": 657,
|
| 1742 |
+
"ಅ": 658,
|
| 1743 |
+
"ಆ": 659,
|
| 1744 |
+
"ಇ": 660,
|
| 1745 |
+
"ಈ": 661,
|
| 1746 |
+
"ಉ": 662,
|
| 1747 |
+
"ಊ": 663,
|
| 1748 |
+
"ಋ": 664,
|
| 1749 |
+
"ಎ": 665,
|
| 1750 |
+
"ಏ": 666,
|
| 1751 |
+
"ಐ": 667,
|
| 1752 |
+
"ಒ": 668,
|
| 1753 |
+
"ಓ": 669,
|
| 1754 |
+
"ಔ": 670,
|
| 1755 |
+
"ಕ": 671,
|
| 1756 |
+
"ಖ": 672,
|
| 1757 |
+
"ಗ": 673,
|
| 1758 |
+
"ಘ": 674,
|
| 1759 |
+
"ಚ": 675,
|
| 1760 |
+
"ಛ": 676,
|
| 1761 |
+
"ಜ": 677,
|
| 1762 |
+
"ಝ": 678,
|
| 1763 |
+
"ಞ": 679,
|
| 1764 |
+
"ಟ": 680,
|
| 1765 |
+
"ಠ": 681,
|
| 1766 |
+
"ಡ": 682,
|
| 1767 |
+
"ಢ": 683,
|
| 1768 |
+
"ಣ": 684,
|
| 1769 |
+
"ತ": 685,
|
| 1770 |
+
"ಥ": 686,
|
| 1771 |
+
"ದ": 687,
|
| 1772 |
+
"ಧ": 688,
|
| 1773 |
+
"ನ": 689,
|
| 1774 |
+
"ಪ": 690,
|
| 1775 |
+
"ಫ": 691,
|
| 1776 |
+
"ಬ": 692,
|
| 1777 |
+
"ಭ": 693,
|
| 1778 |
+
"ಮ": 694,
|
| 1779 |
+
"ಯ": 695,
|
| 1780 |
+
"ರ": 696,
|
| 1781 |
+
"ಲ": 697,
|
| 1782 |
+
"ಳ": 698,
|
| 1783 |
+
"ವ": 699,
|
| 1784 |
+
"ಶ": 700,
|
| 1785 |
+
"ಷ": 701,
|
| 1786 |
+
"ಸ": 702,
|
| 1787 |
+
"ಹ": 703,
|
| 1788 |
+
"಼": 704,
|
| 1789 |
+
"ಾ": 705,
|
| 1790 |
+
"ಿ": 706,
|
| 1791 |
+
"ೀ": 707,
|
| 1792 |
+
"ು": 708,
|
| 1793 |
+
"ೂ": 709,
|
| 1794 |
+
"ೃ": 710,
|
| 1795 |
+
"ೆ": 711,
|
| 1796 |
+
"ೇ": 712,
|
| 1797 |
+
"ೈ": 713,
|
| 1798 |
+
"ೊ": 714,
|
| 1799 |
+
"ೋ": 715,
|
| 1800 |
+
"ೌ": 716,
|
| 1801 |
+
"್": 717,
|
| 1802 |
+
"೦": 718,
|
| 1803 |
+
"೧": 719,
|
| 1804 |
+
"೨": 720,
|
| 1805 |
+
"೩": 721,
|
| 1806 |
+
"೪": 722,
|
| 1807 |
+
"೫": 723,
|
| 1808 |
+
"೬": 724,
|
| 1809 |
+
"೭": 725,
|
| 1810 |
+
"೮": 726,
|
| 1811 |
+
"೯": 727,
|
| 1812 |
+
"ം": 728,
|
| 1813 |
+
"ഃ": 729,
|
| 1814 |
+
"അ": 730,
|
| 1815 |
+
"ആ": 731,
|
| 1816 |
+
"ഇ": 732,
|
| 1817 |
+
"ഈ": 733,
|
| 1818 |
+
"ഉ": 734,
|
| 1819 |
+
"ഊ": 735,
|
| 1820 |
+
"ഋ": 736,
|
| 1821 |
+
"എ": 737,
|
| 1822 |
+
"ഏ": 738,
|
| 1823 |
+
"ഐ": 739,
|
| 1824 |
+
"ഒ": 740,
|
| 1825 |
+
"ഓ": 741,
|
| 1826 |
+
"ഔ": 742,
|
| 1827 |
+
"ക": 743,
|
| 1828 |
+
"ഖ": 744,
|
| 1829 |
+
"ഗ": 745,
|
| 1830 |
+
"ഘ": 746,
|
| 1831 |
+
"ങ": 747,
|
| 1832 |
+
"ച": 748,
|
| 1833 |
+
"ഛ": 749,
|
| 1834 |
+
"ജ": 750,
|
| 1835 |
+
"ഝ": 751,
|
| 1836 |
+
"ഞ": 752,
|
| 1837 |
+
"ട": 753,
|
| 1838 |
+
"ഠ": 754,
|
| 1839 |
+
"ഡ": 755,
|
| 1840 |
+
"ഢ": 756,
|
| 1841 |
+
"ണ": 757,
|
| 1842 |
+
"ത": 758,
|
| 1843 |
+
"ഥ": 759,
|
| 1844 |
+
"ദ": 760,
|
| 1845 |
+
"ധ": 761,
|
| 1846 |
+
"ന": 762,
|
| 1847 |
+
"പ": 763,
|
| 1848 |
+
"ഫ": 764,
|
| 1849 |
+
"ബ": 765,
|
| 1850 |
+
"ഭ": 766,
|
| 1851 |
+
"മ": 767,
|
| 1852 |
+
"യ": 768,
|
| 1853 |
+
"ര": 769,
|
| 1854 |
+
"റ": 770,
|
| 1855 |
+
"ല": 771,
|
| 1856 |
+
"ള": 772,
|
| 1857 |
+
"ഴ": 773,
|
| 1858 |
+
"വ": 774,
|
| 1859 |
+
"ശ": 775,
|
| 1860 |
+
"ഷ": 776,
|
| 1861 |
+
"സ": 777,
|
| 1862 |
+
"ഹ": 778,
|
| 1863 |
+
"ാ": 779,
|
| 1864 |
+
"ി": 780,
|
| 1865 |
+
"ീ": 781,
|
| 1866 |
+
"ു": 782,
|
| 1867 |
+
"ൂ": 783,
|
| 1868 |
+
"ൃ": 784,
|
| 1869 |
+
"െ": 785,
|
| 1870 |
+
"േ": 786,
|
| 1871 |
+
"ൈ": 787,
|
| 1872 |
+
"ൊ": 788,
|
| 1873 |
+
"ോ": 789,
|
| 1874 |
+
"ൌ": 790,
|
| 1875 |
+
"്": 791,
|
| 1876 |
+
"ൗ": 792,
|
| 1877 |
+
"൦": 793,
|
| 1878 |
+
"൧": 794,
|
| 1879 |
+
"൨": 795,
|
| 1880 |
+
"൩": 796,
|
| 1881 |
+
"൪": 797,
|
| 1882 |
+
"൫": 798,
|
| 1883 |
+
"൬": 799,
|
| 1884 |
+
"൭": 800,
|
| 1885 |
+
"൮": 801,
|
| 1886 |
+
"൯": 802,
|
| 1887 |
+
"ൺ": 803,
|
| 1888 |
+
"ൻ": 804,
|
| 1889 |
+
"ർ": 805,
|
| 1890 |
+
"ൽ": 806,
|
| 1891 |
+
"ൾ": 807,
|
| 1892 |
+
"": 808,
|
| 1893 |
+
"": 809,
|
| 1894 |
+
"▁": 810
|
| 1895 |
+
},
|
| 1896 |
+
"merges": []
|
| 1897 |
+
}
|
| 1898 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,1054 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<unk>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"811": {
|
| 12 |
+
"content": "<s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"812": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"813": {
|
| 28 |
+
"content": "<pad>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"814": {
|
| 36 |
+
"content": "<arb>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"815": {
|
| 44 |
+
"content": "<asm>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"816": {
|
| 52 |
+
"content": "<ben>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"817": {
|
| 60 |
+
"content": "<guj>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"818": {
|
| 68 |
+
"content": "<hin>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"819": {
|
| 76 |
+
"content": "<kan>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"820": {
|
| 84 |
+
"content": "<mal>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"821": {
|
| 92 |
+
"content": "<mar>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"822": {
|
| 100 |
+
"content": "<ori>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"823": {
|
| 108 |
+
"content": "<pan>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"824": {
|
| 116 |
+
"content": "<tam>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"825": {
|
| 124 |
+
"content": "<tel>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"826": {
|
| 132 |
+
"content": "<extra_id_0>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"827": {
|
| 140 |
+
"content": "<extra_id_1>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"828": {
|
| 148 |
+
"content": "<extra_id_2>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"829": {
|
| 156 |
+
"content": "<extra_id_3>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"830": {
|
| 164 |
+
"content": "<extra_id_4>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"831": {
|
| 172 |
+
"content": "<extra_id_5>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"832": {
|
| 180 |
+
"content": "<extra_id_6>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"833": {
|
| 188 |
+
"content": "<extra_id_7>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"834": {
|
| 196 |
+
"content": "<extra_id_8>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"835": {
|
| 204 |
+
"content": "<extra_id_9>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"836": {
|
| 212 |
+
"content": "<extra_id_10>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"837": {
|
| 220 |
+
"content": "<extra_id_11>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"838": {
|
| 228 |
+
"content": "<extra_id_12>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"839": {
|
| 236 |
+
"content": "<extra_id_13>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"840": {
|
| 244 |
+
"content": "<extra_id_14>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"841": {
|
| 252 |
+
"content": "<extra_id_15>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"842": {
|
| 260 |
+
"content": "<extra_id_16>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"843": {
|
| 268 |
+
"content": "<extra_id_17>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"844": {
|
| 276 |
+
"content": "<extra_id_18>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"845": {
|
| 284 |
+
"content": "<extra_id_19>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"846": {
|
| 292 |
+
"content": "<extra_id_20>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"847": {
|
| 300 |
+
"content": "<extra_id_21>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"848": {
|
| 308 |
+
"content": "<extra_id_22>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"849": {
|
| 316 |
+
"content": "<extra_id_23>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"850": {
|
| 324 |
+
"content": "<extra_id_24>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"851": {
|
| 332 |
+
"content": "<extra_id_25>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"852": {
|
| 340 |
+
"content": "<extra_id_26>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"853": {
|
| 348 |
+
"content": "<extra_id_27>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"854": {
|
| 356 |
+
"content": "<extra_id_28>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"855": {
|
| 364 |
+
"content": "<extra_id_29>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"856": {
|
| 372 |
+
"content": "<extra_id_30>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"857": {
|
| 380 |
+
"content": "<extra_id_31>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"858": {
|
| 388 |
+
"content": "<extra_id_32>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"859": {
|
| 396 |
+
"content": "<extra_id_33>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"860": {
|
| 404 |
+
"content": "<extra_id_34>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"861": {
|
| 412 |
+
"content": "<extra_id_35>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"862": {
|
| 420 |
+
"content": "<extra_id_36>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"863": {
|
| 428 |
+
"content": "<extra_id_37>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"864": {
|
| 436 |
+
"content": "<extra_id_38>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"865": {
|
| 444 |
+
"content": "<extra_id_39>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"866": {
|
| 452 |
+
"content": "<extra_id_40>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"867": {
|
| 460 |
+
"content": "<extra_id_41>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"868": {
|
| 468 |
+
"content": "<extra_id_42>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"869": {
|
| 476 |
+
"content": "<extra_id_43>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"870": {
|
| 484 |
+
"content": "<extra_id_44>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"871": {
|
| 492 |
+
"content": "<extra_id_45>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"872": {
|
| 500 |
+
"content": "<extra_id_46>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"873": {
|
| 508 |
+
"content": "<extra_id_47>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"874": {
|
| 516 |
+
"content": "<extra_id_48>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"875": {
|
| 524 |
+
"content": "<extra_id_49>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"876": {
|
| 532 |
+
"content": "<extra_id_50>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"877": {
|
| 540 |
+
"content": "<extra_id_51>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"878": {
|
| 548 |
+
"content": "<extra_id_52>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"879": {
|
| 556 |
+
"content": "<extra_id_53>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"880": {
|
| 564 |
+
"content": "<extra_id_54>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"881": {
|
| 572 |
+
"content": "<extra_id_55>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"882": {
|
| 580 |
+
"content": "<extra_id_56>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"883": {
|
| 588 |
+
"content": "<extra_id_57>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"884": {
|
| 596 |
+
"content": "<extra_id_58>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"885": {
|
| 604 |
+
"content": "<extra_id_59>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"886": {
|
| 612 |
+
"content": "<extra_id_60>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"887": {
|
| 620 |
+
"content": "<extra_id_61>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"888": {
|
| 628 |
+
"content": "<extra_id_62>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"889": {
|
| 636 |
+
"content": "<extra_id_63>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"890": {
|
| 644 |
+
"content": "<extra_id_64>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"891": {
|
| 652 |
+
"content": "<extra_id_65>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"892": {
|
| 660 |
+
"content": "<extra_id_66>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"893": {
|
| 668 |
+
"content": "<extra_id_67>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"894": {
|
| 676 |
+
"content": "<extra_id_68>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"895": {
|
| 684 |
+
"content": "<extra_id_69>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"896": {
|
| 692 |
+
"content": "<extra_id_70>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"897": {
|
| 700 |
+
"content": "<extra_id_71>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"898": {
|
| 708 |
+
"content": "<extra_id_72>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"899": {
|
| 716 |
+
"content": "<extra_id_73>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"900": {
|
| 724 |
+
"content": "<extra_id_74>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"901": {
|
| 732 |
+
"content": "<extra_id_75>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"902": {
|
| 740 |
+
"content": "<extra_id_76>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"903": {
|
| 748 |
+
"content": "<extra_id_77>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"904": {
|
| 756 |
+
"content": "<extra_id_78>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"905": {
|
| 764 |
+
"content": "<extra_id_79>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"906": {
|
| 772 |
+
"content": "<extra_id_80>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"907": {
|
| 780 |
+
"content": "<extra_id_81>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"908": {
|
| 788 |
+
"content": "<extra_id_82>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"909": {
|
| 796 |
+
"content": "<extra_id_83>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"910": {
|
| 804 |
+
"content": "<extra_id_84>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"911": {
|
| 812 |
+
"content": "<extra_id_85>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"912": {
|
| 820 |
+
"content": "<extra_id_86>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"913": {
|
| 828 |
+
"content": "<extra_id_87>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"914": {
|
| 836 |
+
"content": "<extra_id_88>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"915": {
|
| 844 |
+
"content": "<extra_id_89>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"916": {
|
| 852 |
+
"content": "<extra_id_90>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"917": {
|
| 860 |
+
"content": "<extra_id_91>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"918": {
|
| 868 |
+
"content": "<extra_id_92>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"919": {
|
| 876 |
+
"content": "<extra_id_93>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"920": {
|
| 884 |
+
"content": "<extra_id_94>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"921": {
|
| 892 |
+
"content": "<extra_id_95>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"922": {
|
| 900 |
+
"content": "<extra_id_96>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"923": {
|
| 908 |
+
"content": "<extra_id_97>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"924": {
|
| 916 |
+
"content": "<extra_id_98>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"925": {
|
| 924 |
+
"content": "<extra_id_99>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
}
|
| 931 |
+
},
|
| 932 |
+
"additional_special_tokens": [
|
| 933 |
+
"<arb>",
|
| 934 |
+
"<asm>",
|
| 935 |
+
"<ben>",
|
| 936 |
+
"<guj>",
|
| 937 |
+
"<hin>",
|
| 938 |
+
"<kan>",
|
| 939 |
+
"<mal>",
|
| 940 |
+
"<mar>",
|
| 941 |
+
"<ori>",
|
| 942 |
+
"<pan>",
|
| 943 |
+
"<tam>",
|
| 944 |
+
"<tel>",
|
| 945 |
+
"<extra_id_0>",
|
| 946 |
+
"<extra_id_1>",
|
| 947 |
+
"<extra_id_2>",
|
| 948 |
+
"<extra_id_3>",
|
| 949 |
+
"<extra_id_4>",
|
| 950 |
+
"<extra_id_5>",
|
| 951 |
+
"<extra_id_6>",
|
| 952 |
+
"<extra_id_7>",
|
| 953 |
+
"<extra_id_8>",
|
| 954 |
+
"<extra_id_9>",
|
| 955 |
+
"<extra_id_10>",
|
| 956 |
+
"<extra_id_11>",
|
| 957 |
+
"<extra_id_12>",
|
| 958 |
+
"<extra_id_13>",
|
| 959 |
+
"<extra_id_14>",
|
| 960 |
+
"<extra_id_15>",
|
| 961 |
+
"<extra_id_16>",
|
| 962 |
+
"<extra_id_17>",
|
| 963 |
+
"<extra_id_18>",
|
| 964 |
+
"<extra_id_19>",
|
| 965 |
+
"<extra_id_20>",
|
| 966 |
+
"<extra_id_21>",
|
| 967 |
+
"<extra_id_22>",
|
| 968 |
+
"<extra_id_23>",
|
| 969 |
+
"<extra_id_24>",
|
| 970 |
+
"<extra_id_25>",
|
| 971 |
+
"<extra_id_26>",
|
| 972 |
+
"<extra_id_27>",
|
| 973 |
+
"<extra_id_28>",
|
| 974 |
+
"<extra_id_29>",
|
| 975 |
+
"<extra_id_30>",
|
| 976 |
+
"<extra_id_31>",
|
| 977 |
+
"<extra_id_32>",
|
| 978 |
+
"<extra_id_33>",
|
| 979 |
+
"<extra_id_34>",
|
| 980 |
+
"<extra_id_35>",
|
| 981 |
+
"<extra_id_36>",
|
| 982 |
+
"<extra_id_37>",
|
| 983 |
+
"<extra_id_38>",
|
| 984 |
+
"<extra_id_39>",
|
| 985 |
+
"<extra_id_40>",
|
| 986 |
+
"<extra_id_41>",
|
| 987 |
+
"<extra_id_42>",
|
| 988 |
+
"<extra_id_43>",
|
| 989 |
+
"<extra_id_44>",
|
| 990 |
+
"<extra_id_45>",
|
| 991 |
+
"<extra_id_46>",
|
| 992 |
+
"<extra_id_47>",
|
| 993 |
+
"<extra_id_48>",
|
| 994 |
+
"<extra_id_49>",
|
| 995 |
+
"<extra_id_50>",
|
| 996 |
+
"<extra_id_51>",
|
| 997 |
+
"<extra_id_52>",
|
| 998 |
+
"<extra_id_53>",
|
| 999 |
+
"<extra_id_54>",
|
| 1000 |
+
"<extra_id_55>",
|
| 1001 |
+
"<extra_id_56>",
|
| 1002 |
+
"<extra_id_57>",
|
| 1003 |
+
"<extra_id_58>",
|
| 1004 |
+
"<extra_id_59>",
|
| 1005 |
+
"<extra_id_60>",
|
| 1006 |
+
"<extra_id_61>",
|
| 1007 |
+
"<extra_id_62>",
|
| 1008 |
+
"<extra_id_63>",
|
| 1009 |
+
"<extra_id_64>",
|
| 1010 |
+
"<extra_id_65>",
|
| 1011 |
+
"<extra_id_66>",
|
| 1012 |
+
"<extra_id_67>",
|
| 1013 |
+
"<extra_id_68>",
|
| 1014 |
+
"<extra_id_69>",
|
| 1015 |
+
"<extra_id_70>",
|
| 1016 |
+
"<extra_id_71>",
|
| 1017 |
+
"<extra_id_72>",
|
| 1018 |
+
"<extra_id_73>",
|
| 1019 |
+
"<extra_id_74>",
|
| 1020 |
+
"<extra_id_75>",
|
| 1021 |
+
"<extra_id_76>",
|
| 1022 |
+
"<extra_id_77>",
|
| 1023 |
+
"<extra_id_78>",
|
| 1024 |
+
"<extra_id_79>",
|
| 1025 |
+
"<extra_id_80>",
|
| 1026 |
+
"<extra_id_81>",
|
| 1027 |
+
"<extra_id_82>",
|
| 1028 |
+
"<extra_id_83>",
|
| 1029 |
+
"<extra_id_84>",
|
| 1030 |
+
"<extra_id_85>",
|
| 1031 |
+
"<extra_id_86>",
|
| 1032 |
+
"<extra_id_87>",
|
| 1033 |
+
"<extra_id_88>",
|
| 1034 |
+
"<extra_id_89>",
|
| 1035 |
+
"<extra_id_90>",
|
| 1036 |
+
"<extra_id_91>",
|
| 1037 |
+
"<extra_id_92>",
|
| 1038 |
+
"<extra_id_93>",
|
| 1039 |
+
"<extra_id_94>",
|
| 1040 |
+
"<extra_id_95>",
|
| 1041 |
+
"<extra_id_96>",
|
| 1042 |
+
"<extra_id_97>",
|
| 1043 |
+
"<extra_id_98>",
|
| 1044 |
+
"<extra_id_99>"
|
| 1045 |
+
],
|
| 1046 |
+
"bos_token": "<s>",
|
| 1047 |
+
"clean_up_tokenization_spaces": false,
|
| 1048 |
+
"eos_token": "</s>",
|
| 1049 |
+
"extra_ids": 100,
|
| 1050 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 1051 |
+
"pad_token": "<pad>",
|
| 1052 |
+
"tokenizer_class": "T5Tokenizer",
|
| 1053 |
+
"unk_token": "<unk>"
|
| 1054 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aaaf75165f97986b66f80749f20de988efe4be07e385bfe7a8219ef19d9ee064
|
| 3 |
+
size 4015
|