Training in progress, epoch 1
Browse files- added_tokens.json +155 -0
- config.json +32 -0
- model.safetensors +3 -0
- special_tokens_map.json +424 -0
- spiece.model +3 -0
- tokenizer_config.json +1321 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,155 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<extra_id_0>": 36095,
|
| 3 |
+
"<extra_id_10>": 36085,
|
| 4 |
+
"<extra_id_11>": 36084,
|
| 5 |
+
"<extra_id_12>": 36083,
|
| 6 |
+
"<extra_id_13>": 36082,
|
| 7 |
+
"<extra_id_14>": 36081,
|
| 8 |
+
"<extra_id_15>": 36080,
|
| 9 |
+
"<extra_id_16>": 36079,
|
| 10 |
+
"<extra_id_17>": 36078,
|
| 11 |
+
"<extra_id_18>": 36077,
|
| 12 |
+
"<extra_id_19>": 36076,
|
| 13 |
+
"<extra_id_1>": 36094,
|
| 14 |
+
"<extra_id_20>": 36075,
|
| 15 |
+
"<extra_id_21>": 36074,
|
| 16 |
+
"<extra_id_22>": 36073,
|
| 17 |
+
"<extra_id_23>": 36072,
|
| 18 |
+
"<extra_id_24>": 36071,
|
| 19 |
+
"<extra_id_25>": 36070,
|
| 20 |
+
"<extra_id_26>": 36069,
|
| 21 |
+
"<extra_id_27>": 36068,
|
| 22 |
+
"<extra_id_28>": 36067,
|
| 23 |
+
"<extra_id_29>": 36066,
|
| 24 |
+
"<extra_id_2>": 36093,
|
| 25 |
+
"<extra_id_30>": 36065,
|
| 26 |
+
"<extra_id_31>": 36064,
|
| 27 |
+
"<extra_id_32>": 36063,
|
| 28 |
+
"<extra_id_33>": 36062,
|
| 29 |
+
"<extra_id_34>": 36061,
|
| 30 |
+
"<extra_id_35>": 36060,
|
| 31 |
+
"<extra_id_36>": 36059,
|
| 32 |
+
"<extra_id_37>": 36058,
|
| 33 |
+
"<extra_id_38>": 36057,
|
| 34 |
+
"<extra_id_39>": 36056,
|
| 35 |
+
"<extra_id_3>": 36092,
|
| 36 |
+
"<extra_id_40>": 36055,
|
| 37 |
+
"<extra_id_41>": 36054,
|
| 38 |
+
"<extra_id_42>": 36053,
|
| 39 |
+
"<extra_id_43>": 36052,
|
| 40 |
+
"<extra_id_44>": 36051,
|
| 41 |
+
"<extra_id_45>": 36050,
|
| 42 |
+
"<extra_id_46>": 36049,
|
| 43 |
+
"<extra_id_47>": 36048,
|
| 44 |
+
"<extra_id_48>": 36047,
|
| 45 |
+
"<extra_id_49>": 36046,
|
| 46 |
+
"<extra_id_4>": 36091,
|
| 47 |
+
"<extra_id_50>": 36045,
|
| 48 |
+
"<extra_id_51>": 36044,
|
| 49 |
+
"<extra_id_52>": 36043,
|
| 50 |
+
"<extra_id_53>": 36042,
|
| 51 |
+
"<extra_id_54>": 36041,
|
| 52 |
+
"<extra_id_55>": 36040,
|
| 53 |
+
"<extra_id_56>": 36039,
|
| 54 |
+
"<extra_id_57>": 36038,
|
| 55 |
+
"<extra_id_58>": 36037,
|
| 56 |
+
"<extra_id_59>": 36036,
|
| 57 |
+
"<extra_id_5>": 36090,
|
| 58 |
+
"<extra_id_60>": 36035,
|
| 59 |
+
"<extra_id_61>": 36034,
|
| 60 |
+
"<extra_id_62>": 36033,
|
| 61 |
+
"<extra_id_63>": 36032,
|
| 62 |
+
"<extra_id_64>": 36031,
|
| 63 |
+
"<extra_id_65>": 36030,
|
| 64 |
+
"<extra_id_66>": 36029,
|
| 65 |
+
"<extra_id_67>": 36028,
|
| 66 |
+
"<extra_id_68>": 36027,
|
| 67 |
+
"<extra_id_69>": 36026,
|
| 68 |
+
"<extra_id_6>": 36089,
|
| 69 |
+
"<extra_id_70>": 36025,
|
| 70 |
+
"<extra_id_71>": 36024,
|
| 71 |
+
"<extra_id_72>": 36023,
|
| 72 |
+
"<extra_id_73>": 36022,
|
| 73 |
+
"<extra_id_74>": 36021,
|
| 74 |
+
"<extra_id_75>": 36020,
|
| 75 |
+
"<extra_id_76>": 36019,
|
| 76 |
+
"<extra_id_77>": 36018,
|
| 77 |
+
"<extra_id_78>": 36017,
|
| 78 |
+
"<extra_id_79>": 36016,
|
| 79 |
+
"<extra_id_7>": 36088,
|
| 80 |
+
"<extra_id_80>": 36015,
|
| 81 |
+
"<extra_id_81>": 36014,
|
| 82 |
+
"<extra_id_82>": 36013,
|
| 83 |
+
"<extra_id_83>": 36012,
|
| 84 |
+
"<extra_id_84>": 36011,
|
| 85 |
+
"<extra_id_85>": 36010,
|
| 86 |
+
"<extra_id_86>": 36009,
|
| 87 |
+
"<extra_id_87>": 36008,
|
| 88 |
+
"<extra_id_88>": 36007,
|
| 89 |
+
"<extra_id_89>": 36006,
|
| 90 |
+
"<extra_id_8>": 36087,
|
| 91 |
+
"<extra_id_90>": 36005,
|
| 92 |
+
"<extra_id_91>": 36004,
|
| 93 |
+
"<extra_id_92>": 36003,
|
| 94 |
+
"<extra_id_93>": 36002,
|
| 95 |
+
"<extra_id_94>": 36001,
|
| 96 |
+
"<extra_id_95>": 36000,
|
| 97 |
+
"<extra_id_9>": 36086,
|
| 98 |
+
"LEX_10": 36135,
|
| 99 |
+
"LEX_15": 36136,
|
| 100 |
+
"LEX_20": 36137,
|
| 101 |
+
"LEX_25": 36138,
|
| 102 |
+
"LEX_30": 36139,
|
| 103 |
+
"LEX_35": 36140,
|
| 104 |
+
"LEX_40": 36141,
|
| 105 |
+
"LEX_45": 36142,
|
| 106 |
+
"LEX_5": 36134,
|
| 107 |
+
"LEX_50": 36143,
|
| 108 |
+
"LEX_55": 36144,
|
| 109 |
+
"LEX_60": 36145,
|
| 110 |
+
"LEX_65": 36146,
|
| 111 |
+
"LEX_70": 36147,
|
| 112 |
+
"LEX_75": 36148,
|
| 113 |
+
"LEX_80": 36149,
|
| 114 |
+
"LEX_85": 36150,
|
| 115 |
+
"LEX_90": 36151,
|
| 116 |
+
"LEX_95": 36152,
|
| 117 |
+
"SEM_10": 36097,
|
| 118 |
+
"SEM_15": 36098,
|
| 119 |
+
"SEM_20": 36099,
|
| 120 |
+
"SEM_25": 36100,
|
| 121 |
+
"SEM_30": 36101,
|
| 122 |
+
"SEM_35": 36102,
|
| 123 |
+
"SEM_40": 36103,
|
| 124 |
+
"SEM_45": 36104,
|
| 125 |
+
"SEM_5": 36096,
|
| 126 |
+
"SEM_50": 36105,
|
| 127 |
+
"SEM_55": 36106,
|
| 128 |
+
"SEM_60": 36107,
|
| 129 |
+
"SEM_65": 36108,
|
| 130 |
+
"SEM_70": 36109,
|
| 131 |
+
"SEM_75": 36110,
|
| 132 |
+
"SEM_80": 36111,
|
| 133 |
+
"SEM_85": 36112,
|
| 134 |
+
"SEM_90": 36113,
|
| 135 |
+
"SEM_95": 36114,
|
| 136 |
+
"SYN_10": 36116,
|
| 137 |
+
"SYN_15": 36117,
|
| 138 |
+
"SYN_20": 36118,
|
| 139 |
+
"SYN_25": 36119,
|
| 140 |
+
"SYN_30": 36120,
|
| 141 |
+
"SYN_35": 36121,
|
| 142 |
+
"SYN_40": 36122,
|
| 143 |
+
"SYN_45": 36123,
|
| 144 |
+
"SYN_5": 36115,
|
| 145 |
+
"SYN_50": 36124,
|
| 146 |
+
"SYN_55": 36125,
|
| 147 |
+
"SYN_60": 36126,
|
| 148 |
+
"SYN_65": 36127,
|
| 149 |
+
"SYN_70": 36128,
|
| 150 |
+
"SYN_75": 36129,
|
| 151 |
+
"SYN_80": 36130,
|
| 152 |
+
"SYN_85": 36131,
|
| 153 |
+
"SYN_90": 36132,
|
| 154 |
+
"SYN_95": 36133
|
| 155 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "ngwgsang/vit5-student",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 3072,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 768,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "relu",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "relu",
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": false,
|
| 18 |
+
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"model_type": "t5",
|
| 20 |
+
"n_positions": 512,
|
| 21 |
+
"num_decoder_layers": 12,
|
| 22 |
+
"num_heads": 12,
|
| 23 |
+
"num_layers": 12,
|
| 24 |
+
"output_past": true,
|
| 25 |
+
"pad_token_id": 0,
|
| 26 |
+
"relative_attention_max_distance": 128,
|
| 27 |
+
"relative_attention_num_buckets": 32,
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.44.2",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 36153
|
| 32 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:062a40993003e3360c210e03da243660253cf520868ffed7f56e60dcaf5289da
|
| 3 |
+
size 904009512
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,424 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "SEM_5",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"content": "SEM_10",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": false,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"content": "SEM_15",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"content": "SEM_20",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"content": "SEM_25",
|
| 33 |
+
"lstrip": false,
|
| 34 |
+
"normalized": false,
|
| 35 |
+
"rstrip": false,
|
| 36 |
+
"single_word": false
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"content": "SEM_30",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"content": "SEM_35",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"content": "SEM_40",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"content": "SEM_45",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"content": "SEM_50",
|
| 68 |
+
"lstrip": false,
|
| 69 |
+
"normalized": false,
|
| 70 |
+
"rstrip": false,
|
| 71 |
+
"single_word": false
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"content": "SEM_55",
|
| 75 |
+
"lstrip": false,
|
| 76 |
+
"normalized": false,
|
| 77 |
+
"rstrip": false,
|
| 78 |
+
"single_word": false
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"content": "SEM_60",
|
| 82 |
+
"lstrip": false,
|
| 83 |
+
"normalized": false,
|
| 84 |
+
"rstrip": false,
|
| 85 |
+
"single_word": false
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"content": "SEM_65",
|
| 89 |
+
"lstrip": false,
|
| 90 |
+
"normalized": false,
|
| 91 |
+
"rstrip": false,
|
| 92 |
+
"single_word": false
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"content": "SEM_70",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"content": "SEM_75",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"content": "SEM_80",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"content": "SEM_85",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"content": "SEM_90",
|
| 124 |
+
"lstrip": false,
|
| 125 |
+
"normalized": false,
|
| 126 |
+
"rstrip": false,
|
| 127 |
+
"single_word": false
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"content": "SEM_95",
|
| 131 |
+
"lstrip": false,
|
| 132 |
+
"normalized": false,
|
| 133 |
+
"rstrip": false,
|
| 134 |
+
"single_word": false
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"content": "SYN_5",
|
| 138 |
+
"lstrip": false,
|
| 139 |
+
"normalized": false,
|
| 140 |
+
"rstrip": false,
|
| 141 |
+
"single_word": false
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"content": "SYN_10",
|
| 145 |
+
"lstrip": false,
|
| 146 |
+
"normalized": false,
|
| 147 |
+
"rstrip": false,
|
| 148 |
+
"single_word": false
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"content": "SYN_15",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": false,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"content": "SYN_20",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"content": "SYN_25",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"content": "SYN_30",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"content": "SYN_35",
|
| 180 |
+
"lstrip": false,
|
| 181 |
+
"normalized": false,
|
| 182 |
+
"rstrip": false,
|
| 183 |
+
"single_word": false
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"content": "SYN_40",
|
| 187 |
+
"lstrip": false,
|
| 188 |
+
"normalized": false,
|
| 189 |
+
"rstrip": false,
|
| 190 |
+
"single_word": false
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"content": "SYN_45",
|
| 194 |
+
"lstrip": false,
|
| 195 |
+
"normalized": false,
|
| 196 |
+
"rstrip": false,
|
| 197 |
+
"single_word": false
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"content": "SYN_50",
|
| 201 |
+
"lstrip": false,
|
| 202 |
+
"normalized": false,
|
| 203 |
+
"rstrip": false,
|
| 204 |
+
"single_word": false
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"content": "SYN_55",
|
| 208 |
+
"lstrip": false,
|
| 209 |
+
"normalized": false,
|
| 210 |
+
"rstrip": false,
|
| 211 |
+
"single_word": false
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"content": "SYN_60",
|
| 215 |
+
"lstrip": false,
|
| 216 |
+
"normalized": false,
|
| 217 |
+
"rstrip": false,
|
| 218 |
+
"single_word": false
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"content": "SYN_65",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": false,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"content": "SYN_70",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"content": "SYN_75",
|
| 236 |
+
"lstrip": false,
|
| 237 |
+
"normalized": false,
|
| 238 |
+
"rstrip": false,
|
| 239 |
+
"single_word": false
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"content": "SYN_80",
|
| 243 |
+
"lstrip": false,
|
| 244 |
+
"normalized": false,
|
| 245 |
+
"rstrip": false,
|
| 246 |
+
"single_word": false
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"content": "SYN_85",
|
| 250 |
+
"lstrip": false,
|
| 251 |
+
"normalized": false,
|
| 252 |
+
"rstrip": false,
|
| 253 |
+
"single_word": false
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"content": "SYN_90",
|
| 257 |
+
"lstrip": false,
|
| 258 |
+
"normalized": false,
|
| 259 |
+
"rstrip": false,
|
| 260 |
+
"single_word": false
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"content": "SYN_95",
|
| 264 |
+
"lstrip": false,
|
| 265 |
+
"normalized": false,
|
| 266 |
+
"rstrip": false,
|
| 267 |
+
"single_word": false
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"content": "LEX_5",
|
| 271 |
+
"lstrip": false,
|
| 272 |
+
"normalized": false,
|
| 273 |
+
"rstrip": false,
|
| 274 |
+
"single_word": false
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"content": "LEX_10",
|
| 278 |
+
"lstrip": false,
|
| 279 |
+
"normalized": false,
|
| 280 |
+
"rstrip": false,
|
| 281 |
+
"single_word": false
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"content": "LEX_15",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"content": "LEX_20",
|
| 292 |
+
"lstrip": false,
|
| 293 |
+
"normalized": false,
|
| 294 |
+
"rstrip": false,
|
| 295 |
+
"single_word": false
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"content": "LEX_25",
|
| 299 |
+
"lstrip": false,
|
| 300 |
+
"normalized": false,
|
| 301 |
+
"rstrip": false,
|
| 302 |
+
"single_word": false
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"content": "LEX_30",
|
| 306 |
+
"lstrip": false,
|
| 307 |
+
"normalized": false,
|
| 308 |
+
"rstrip": false,
|
| 309 |
+
"single_word": false
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"content": "LEX_35",
|
| 313 |
+
"lstrip": false,
|
| 314 |
+
"normalized": false,
|
| 315 |
+
"rstrip": false,
|
| 316 |
+
"single_word": false
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"content": "LEX_40",
|
| 320 |
+
"lstrip": false,
|
| 321 |
+
"normalized": false,
|
| 322 |
+
"rstrip": false,
|
| 323 |
+
"single_word": false
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"content": "LEX_45",
|
| 327 |
+
"lstrip": false,
|
| 328 |
+
"normalized": false,
|
| 329 |
+
"rstrip": false,
|
| 330 |
+
"single_word": false
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"content": "LEX_50",
|
| 334 |
+
"lstrip": false,
|
| 335 |
+
"normalized": false,
|
| 336 |
+
"rstrip": false,
|
| 337 |
+
"single_word": false
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"content": "LEX_55",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"content": "LEX_60",
|
| 348 |
+
"lstrip": false,
|
| 349 |
+
"normalized": false,
|
| 350 |
+
"rstrip": false,
|
| 351 |
+
"single_word": false
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"content": "LEX_65",
|
| 355 |
+
"lstrip": false,
|
| 356 |
+
"normalized": false,
|
| 357 |
+
"rstrip": false,
|
| 358 |
+
"single_word": false
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"content": "LEX_70",
|
| 362 |
+
"lstrip": false,
|
| 363 |
+
"normalized": false,
|
| 364 |
+
"rstrip": false,
|
| 365 |
+
"single_word": false
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"content": "LEX_75",
|
| 369 |
+
"lstrip": false,
|
| 370 |
+
"normalized": false,
|
| 371 |
+
"rstrip": false,
|
| 372 |
+
"single_word": false
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"content": "LEX_80",
|
| 376 |
+
"lstrip": false,
|
| 377 |
+
"normalized": false,
|
| 378 |
+
"rstrip": false,
|
| 379 |
+
"single_word": false
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"content": "LEX_85",
|
| 383 |
+
"lstrip": false,
|
| 384 |
+
"normalized": false,
|
| 385 |
+
"rstrip": false,
|
| 386 |
+
"single_word": false
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"content": "LEX_90",
|
| 390 |
+
"lstrip": false,
|
| 391 |
+
"normalized": false,
|
| 392 |
+
"rstrip": false,
|
| 393 |
+
"single_word": false
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"content": "LEX_95",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false
|
| 401 |
+
}
|
| 402 |
+
],
|
| 403 |
+
"eos_token": {
|
| 404 |
+
"content": "</s>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false
|
| 409 |
+
},
|
| 410 |
+
"pad_token": {
|
| 411 |
+
"content": "<pad>",
|
| 412 |
+
"lstrip": false,
|
| 413 |
+
"normalized": false,
|
| 414 |
+
"rstrip": false,
|
| 415 |
+
"single_word": false
|
| 416 |
+
},
|
| 417 |
+
"unk_token": {
|
| 418 |
+
"content": "<unk>",
|
| 419 |
+
"lstrip": false,
|
| 420 |
+
"normalized": false,
|
| 421 |
+
"rstrip": false,
|
| 422 |
+
"single_word": false
|
| 423 |
+
}
|
| 424 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59986b62f9f0b90edafb9b073ea7b93d21114a5841219a1ea2399ade73f729c6
|
| 3 |
+
size 820370
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,1321 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<pad>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "</s>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "<unk>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"36000": {
|
| 29 |
+
"content": "<extra_id_95>",
|
| 30 |
+
"lstrip": true,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": true,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"36001": {
|
| 37 |
+
"content": "<extra_id_94>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": true,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"36002": {
|
| 45 |
+
"content": "<extra_id_93>",
|
| 46 |
+
"lstrip": true,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": true,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"36003": {
|
| 53 |
+
"content": "<extra_id_92>",
|
| 54 |
+
"lstrip": true,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": true,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"36004": {
|
| 61 |
+
"content": "<extra_id_91>",
|
| 62 |
+
"lstrip": true,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": true,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"36005": {
|
| 69 |
+
"content": "<extra_id_90>",
|
| 70 |
+
"lstrip": true,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": true,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"36006": {
|
| 77 |
+
"content": "<extra_id_89>",
|
| 78 |
+
"lstrip": true,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": true,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"36007": {
|
| 85 |
+
"content": "<extra_id_88>",
|
| 86 |
+
"lstrip": true,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": true,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"36008": {
|
| 93 |
+
"content": "<extra_id_87>",
|
| 94 |
+
"lstrip": true,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": true,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"36009": {
|
| 101 |
+
"content": "<extra_id_86>",
|
| 102 |
+
"lstrip": true,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": true,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"36010": {
|
| 109 |
+
"content": "<extra_id_85>",
|
| 110 |
+
"lstrip": true,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": true,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"36011": {
|
| 117 |
+
"content": "<extra_id_84>",
|
| 118 |
+
"lstrip": true,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": true,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"36012": {
|
| 125 |
+
"content": "<extra_id_83>",
|
| 126 |
+
"lstrip": true,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": true,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"36013": {
|
| 133 |
+
"content": "<extra_id_82>",
|
| 134 |
+
"lstrip": true,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": true,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
},
|
| 140 |
+
"36014": {
|
| 141 |
+
"content": "<extra_id_81>",
|
| 142 |
+
"lstrip": true,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": true,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": true
|
| 147 |
+
},
|
| 148 |
+
"36015": {
|
| 149 |
+
"content": "<extra_id_80>",
|
| 150 |
+
"lstrip": true,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": true,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": true
|
| 155 |
+
},
|
| 156 |
+
"36016": {
|
| 157 |
+
"content": "<extra_id_79>",
|
| 158 |
+
"lstrip": true,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": true,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": true
|
| 163 |
+
},
|
| 164 |
+
"36017": {
|
| 165 |
+
"content": "<extra_id_78>",
|
| 166 |
+
"lstrip": true,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": true,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": true
|
| 171 |
+
},
|
| 172 |
+
"36018": {
|
| 173 |
+
"content": "<extra_id_77>",
|
| 174 |
+
"lstrip": true,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": true,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": true
|
| 179 |
+
},
|
| 180 |
+
"36019": {
|
| 181 |
+
"content": "<extra_id_76>",
|
| 182 |
+
"lstrip": true,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"rstrip": true,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": true
|
| 187 |
+
},
|
| 188 |
+
"36020": {
|
| 189 |
+
"content": "<extra_id_75>",
|
| 190 |
+
"lstrip": true,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"rstrip": true,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": true
|
| 195 |
+
},
|
| 196 |
+
"36021": {
|
| 197 |
+
"content": "<extra_id_74>",
|
| 198 |
+
"lstrip": true,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"rstrip": true,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": true
|
| 203 |
+
},
|
| 204 |
+
"36022": {
|
| 205 |
+
"content": "<extra_id_73>",
|
| 206 |
+
"lstrip": true,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"rstrip": true,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": true
|
| 211 |
+
},
|
| 212 |
+
"36023": {
|
| 213 |
+
"content": "<extra_id_72>",
|
| 214 |
+
"lstrip": true,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"rstrip": true,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": true
|
| 219 |
+
},
|
| 220 |
+
"36024": {
|
| 221 |
+
"content": "<extra_id_71>",
|
| 222 |
+
"lstrip": true,
|
| 223 |
+
"normalized": false,
|
| 224 |
+
"rstrip": true,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": true
|
| 227 |
+
},
|
| 228 |
+
"36025": {
|
| 229 |
+
"content": "<extra_id_70>",
|
| 230 |
+
"lstrip": true,
|
| 231 |
+
"normalized": false,
|
| 232 |
+
"rstrip": true,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": true
|
| 235 |
+
},
|
| 236 |
+
"36026": {
|
| 237 |
+
"content": "<extra_id_69>",
|
| 238 |
+
"lstrip": true,
|
| 239 |
+
"normalized": false,
|
| 240 |
+
"rstrip": true,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": true
|
| 243 |
+
},
|
| 244 |
+
"36027": {
|
| 245 |
+
"content": "<extra_id_68>",
|
| 246 |
+
"lstrip": true,
|
| 247 |
+
"normalized": false,
|
| 248 |
+
"rstrip": true,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": true
|
| 251 |
+
},
|
| 252 |
+
"36028": {
|
| 253 |
+
"content": "<extra_id_67>",
|
| 254 |
+
"lstrip": true,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"rstrip": true,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": true
|
| 259 |
+
},
|
| 260 |
+
"36029": {
|
| 261 |
+
"content": "<extra_id_66>",
|
| 262 |
+
"lstrip": true,
|
| 263 |
+
"normalized": false,
|
| 264 |
+
"rstrip": true,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": true
|
| 267 |
+
},
|
| 268 |
+
"36030": {
|
| 269 |
+
"content": "<extra_id_65>",
|
| 270 |
+
"lstrip": true,
|
| 271 |
+
"normalized": false,
|
| 272 |
+
"rstrip": true,
|
| 273 |
+
"single_word": false,
|
| 274 |
+
"special": true
|
| 275 |
+
},
|
| 276 |
+
"36031": {
|
| 277 |
+
"content": "<extra_id_64>",
|
| 278 |
+
"lstrip": true,
|
| 279 |
+
"normalized": false,
|
| 280 |
+
"rstrip": true,
|
| 281 |
+
"single_word": false,
|
| 282 |
+
"special": true
|
| 283 |
+
},
|
| 284 |
+
"36032": {
|
| 285 |
+
"content": "<extra_id_63>",
|
| 286 |
+
"lstrip": true,
|
| 287 |
+
"normalized": false,
|
| 288 |
+
"rstrip": true,
|
| 289 |
+
"single_word": false,
|
| 290 |
+
"special": true
|
| 291 |
+
},
|
| 292 |
+
"36033": {
|
| 293 |
+
"content": "<extra_id_62>",
|
| 294 |
+
"lstrip": true,
|
| 295 |
+
"normalized": false,
|
| 296 |
+
"rstrip": true,
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"special": true
|
| 299 |
+
},
|
| 300 |
+
"36034": {
|
| 301 |
+
"content": "<extra_id_61>",
|
| 302 |
+
"lstrip": true,
|
| 303 |
+
"normalized": false,
|
| 304 |
+
"rstrip": true,
|
| 305 |
+
"single_word": false,
|
| 306 |
+
"special": true
|
| 307 |
+
},
|
| 308 |
+
"36035": {
|
| 309 |
+
"content": "<extra_id_60>",
|
| 310 |
+
"lstrip": true,
|
| 311 |
+
"normalized": false,
|
| 312 |
+
"rstrip": true,
|
| 313 |
+
"single_word": false,
|
| 314 |
+
"special": true
|
| 315 |
+
},
|
| 316 |
+
"36036": {
|
| 317 |
+
"content": "<extra_id_59>",
|
| 318 |
+
"lstrip": true,
|
| 319 |
+
"normalized": false,
|
| 320 |
+
"rstrip": true,
|
| 321 |
+
"single_word": false,
|
| 322 |
+
"special": true
|
| 323 |
+
},
|
| 324 |
+
"36037": {
|
| 325 |
+
"content": "<extra_id_58>",
|
| 326 |
+
"lstrip": true,
|
| 327 |
+
"normalized": false,
|
| 328 |
+
"rstrip": true,
|
| 329 |
+
"single_word": false,
|
| 330 |
+
"special": true
|
| 331 |
+
},
|
| 332 |
+
"36038": {
|
| 333 |
+
"content": "<extra_id_57>",
|
| 334 |
+
"lstrip": true,
|
| 335 |
+
"normalized": false,
|
| 336 |
+
"rstrip": true,
|
| 337 |
+
"single_word": false,
|
| 338 |
+
"special": true
|
| 339 |
+
},
|
| 340 |
+
"36039": {
|
| 341 |
+
"content": "<extra_id_56>",
|
| 342 |
+
"lstrip": true,
|
| 343 |
+
"normalized": false,
|
| 344 |
+
"rstrip": true,
|
| 345 |
+
"single_word": false,
|
| 346 |
+
"special": true
|
| 347 |
+
},
|
| 348 |
+
"36040": {
|
| 349 |
+
"content": "<extra_id_55>",
|
| 350 |
+
"lstrip": true,
|
| 351 |
+
"normalized": false,
|
| 352 |
+
"rstrip": true,
|
| 353 |
+
"single_word": false,
|
| 354 |
+
"special": true
|
| 355 |
+
},
|
| 356 |
+
"36041": {
|
| 357 |
+
"content": "<extra_id_54>",
|
| 358 |
+
"lstrip": true,
|
| 359 |
+
"normalized": false,
|
| 360 |
+
"rstrip": true,
|
| 361 |
+
"single_word": false,
|
| 362 |
+
"special": true
|
| 363 |
+
},
|
| 364 |
+
"36042": {
|
| 365 |
+
"content": "<extra_id_53>",
|
| 366 |
+
"lstrip": true,
|
| 367 |
+
"normalized": false,
|
| 368 |
+
"rstrip": true,
|
| 369 |
+
"single_word": false,
|
| 370 |
+
"special": true
|
| 371 |
+
},
|
| 372 |
+
"36043": {
|
| 373 |
+
"content": "<extra_id_52>",
|
| 374 |
+
"lstrip": true,
|
| 375 |
+
"normalized": false,
|
| 376 |
+
"rstrip": true,
|
| 377 |
+
"single_word": false,
|
| 378 |
+
"special": true
|
| 379 |
+
},
|
| 380 |
+
"36044": {
|
| 381 |
+
"content": "<extra_id_51>",
|
| 382 |
+
"lstrip": true,
|
| 383 |
+
"normalized": false,
|
| 384 |
+
"rstrip": true,
|
| 385 |
+
"single_word": false,
|
| 386 |
+
"special": true
|
| 387 |
+
},
|
| 388 |
+
"36045": {
|
| 389 |
+
"content": "<extra_id_50>",
|
| 390 |
+
"lstrip": true,
|
| 391 |
+
"normalized": false,
|
| 392 |
+
"rstrip": true,
|
| 393 |
+
"single_word": false,
|
| 394 |
+
"special": true
|
| 395 |
+
},
|
| 396 |
+
"36046": {
|
| 397 |
+
"content": "<extra_id_49>",
|
| 398 |
+
"lstrip": true,
|
| 399 |
+
"normalized": false,
|
| 400 |
+
"rstrip": true,
|
| 401 |
+
"single_word": false,
|
| 402 |
+
"special": true
|
| 403 |
+
},
|
| 404 |
+
"36047": {
|
| 405 |
+
"content": "<extra_id_48>",
|
| 406 |
+
"lstrip": true,
|
| 407 |
+
"normalized": false,
|
| 408 |
+
"rstrip": true,
|
| 409 |
+
"single_word": false,
|
| 410 |
+
"special": true
|
| 411 |
+
},
|
| 412 |
+
"36048": {
|
| 413 |
+
"content": "<extra_id_47>",
|
| 414 |
+
"lstrip": true,
|
| 415 |
+
"normalized": false,
|
| 416 |
+
"rstrip": true,
|
| 417 |
+
"single_word": false,
|
| 418 |
+
"special": true
|
| 419 |
+
},
|
| 420 |
+
"36049": {
|
| 421 |
+
"content": "<extra_id_46>",
|
| 422 |
+
"lstrip": true,
|
| 423 |
+
"normalized": false,
|
| 424 |
+
"rstrip": true,
|
| 425 |
+
"single_word": false,
|
| 426 |
+
"special": true
|
| 427 |
+
},
|
| 428 |
+
"36050": {
|
| 429 |
+
"content": "<extra_id_45>",
|
| 430 |
+
"lstrip": true,
|
| 431 |
+
"normalized": false,
|
| 432 |
+
"rstrip": true,
|
| 433 |
+
"single_word": false,
|
| 434 |
+
"special": true
|
| 435 |
+
},
|
| 436 |
+
"36051": {
|
| 437 |
+
"content": "<extra_id_44>",
|
| 438 |
+
"lstrip": true,
|
| 439 |
+
"normalized": false,
|
| 440 |
+
"rstrip": true,
|
| 441 |
+
"single_word": false,
|
| 442 |
+
"special": true
|
| 443 |
+
},
|
| 444 |
+
"36052": {
|
| 445 |
+
"content": "<extra_id_43>",
|
| 446 |
+
"lstrip": true,
|
| 447 |
+
"normalized": false,
|
| 448 |
+
"rstrip": true,
|
| 449 |
+
"single_word": false,
|
| 450 |
+
"special": true
|
| 451 |
+
},
|
| 452 |
+
"36053": {
|
| 453 |
+
"content": "<extra_id_42>",
|
| 454 |
+
"lstrip": true,
|
| 455 |
+
"normalized": false,
|
| 456 |
+
"rstrip": true,
|
| 457 |
+
"single_word": false,
|
| 458 |
+
"special": true
|
| 459 |
+
},
|
| 460 |
+
"36054": {
|
| 461 |
+
"content": "<extra_id_41>",
|
| 462 |
+
"lstrip": true,
|
| 463 |
+
"normalized": false,
|
| 464 |
+
"rstrip": true,
|
| 465 |
+
"single_word": false,
|
| 466 |
+
"special": true
|
| 467 |
+
},
|
| 468 |
+
"36055": {
|
| 469 |
+
"content": "<extra_id_40>",
|
| 470 |
+
"lstrip": true,
|
| 471 |
+
"normalized": false,
|
| 472 |
+
"rstrip": true,
|
| 473 |
+
"single_word": false,
|
| 474 |
+
"special": true
|
| 475 |
+
},
|
| 476 |
+
"36056": {
|
| 477 |
+
"content": "<extra_id_39>",
|
| 478 |
+
"lstrip": true,
|
| 479 |
+
"normalized": false,
|
| 480 |
+
"rstrip": true,
|
| 481 |
+
"single_word": false,
|
| 482 |
+
"special": true
|
| 483 |
+
},
|
| 484 |
+
"36057": {
|
| 485 |
+
"content": "<extra_id_38>",
|
| 486 |
+
"lstrip": true,
|
| 487 |
+
"normalized": false,
|
| 488 |
+
"rstrip": true,
|
| 489 |
+
"single_word": false,
|
| 490 |
+
"special": true
|
| 491 |
+
},
|
| 492 |
+
"36058": {
|
| 493 |
+
"content": "<extra_id_37>",
|
| 494 |
+
"lstrip": true,
|
| 495 |
+
"normalized": false,
|
| 496 |
+
"rstrip": true,
|
| 497 |
+
"single_word": false,
|
| 498 |
+
"special": true
|
| 499 |
+
},
|
| 500 |
+
"36059": {
|
| 501 |
+
"content": "<extra_id_36>",
|
| 502 |
+
"lstrip": true,
|
| 503 |
+
"normalized": false,
|
| 504 |
+
"rstrip": true,
|
| 505 |
+
"single_word": false,
|
| 506 |
+
"special": true
|
| 507 |
+
},
|
| 508 |
+
"36060": {
|
| 509 |
+
"content": "<extra_id_35>",
|
| 510 |
+
"lstrip": true,
|
| 511 |
+
"normalized": false,
|
| 512 |
+
"rstrip": true,
|
| 513 |
+
"single_word": false,
|
| 514 |
+
"special": true
|
| 515 |
+
},
|
| 516 |
+
"36061": {
|
| 517 |
+
"content": "<extra_id_34>",
|
| 518 |
+
"lstrip": true,
|
| 519 |
+
"normalized": false,
|
| 520 |
+
"rstrip": true,
|
| 521 |
+
"single_word": false,
|
| 522 |
+
"special": true
|
| 523 |
+
},
|
| 524 |
+
"36062": {
|
| 525 |
+
"content": "<extra_id_33>",
|
| 526 |
+
"lstrip": true,
|
| 527 |
+
"normalized": false,
|
| 528 |
+
"rstrip": true,
|
| 529 |
+
"single_word": false,
|
| 530 |
+
"special": true
|
| 531 |
+
},
|
| 532 |
+
"36063": {
|
| 533 |
+
"content": "<extra_id_32>",
|
| 534 |
+
"lstrip": true,
|
| 535 |
+
"normalized": false,
|
| 536 |
+
"rstrip": true,
|
| 537 |
+
"single_word": false,
|
| 538 |
+
"special": true
|
| 539 |
+
},
|
| 540 |
+
"36064": {
|
| 541 |
+
"content": "<extra_id_31>",
|
| 542 |
+
"lstrip": true,
|
| 543 |
+
"normalized": false,
|
| 544 |
+
"rstrip": true,
|
| 545 |
+
"single_word": false,
|
| 546 |
+
"special": true
|
| 547 |
+
},
|
| 548 |
+
"36065": {
|
| 549 |
+
"content": "<extra_id_30>",
|
| 550 |
+
"lstrip": true,
|
| 551 |
+
"normalized": false,
|
| 552 |
+
"rstrip": true,
|
| 553 |
+
"single_word": false,
|
| 554 |
+
"special": true
|
| 555 |
+
},
|
| 556 |
+
"36066": {
|
| 557 |
+
"content": "<extra_id_29>",
|
| 558 |
+
"lstrip": true,
|
| 559 |
+
"normalized": false,
|
| 560 |
+
"rstrip": true,
|
| 561 |
+
"single_word": false,
|
| 562 |
+
"special": true
|
| 563 |
+
},
|
| 564 |
+
"36067": {
|
| 565 |
+
"content": "<extra_id_28>",
|
| 566 |
+
"lstrip": true,
|
| 567 |
+
"normalized": false,
|
| 568 |
+
"rstrip": true,
|
| 569 |
+
"single_word": false,
|
| 570 |
+
"special": true
|
| 571 |
+
},
|
| 572 |
+
"36068": {
|
| 573 |
+
"content": "<extra_id_27>",
|
| 574 |
+
"lstrip": true,
|
| 575 |
+
"normalized": false,
|
| 576 |
+
"rstrip": true,
|
| 577 |
+
"single_word": false,
|
| 578 |
+
"special": true
|
| 579 |
+
},
|
| 580 |
+
"36069": {
|
| 581 |
+
"content": "<extra_id_26>",
|
| 582 |
+
"lstrip": true,
|
| 583 |
+
"normalized": false,
|
| 584 |
+
"rstrip": true,
|
| 585 |
+
"single_word": false,
|
| 586 |
+
"special": true
|
| 587 |
+
},
|
| 588 |
+
"36070": {
|
| 589 |
+
"content": "<extra_id_25>",
|
| 590 |
+
"lstrip": true,
|
| 591 |
+
"normalized": false,
|
| 592 |
+
"rstrip": true,
|
| 593 |
+
"single_word": false,
|
| 594 |
+
"special": true
|
| 595 |
+
},
|
| 596 |
+
"36071": {
|
| 597 |
+
"content": "<extra_id_24>",
|
| 598 |
+
"lstrip": true,
|
| 599 |
+
"normalized": false,
|
| 600 |
+
"rstrip": true,
|
| 601 |
+
"single_word": false,
|
| 602 |
+
"special": true
|
| 603 |
+
},
|
| 604 |
+
"36072": {
|
| 605 |
+
"content": "<extra_id_23>",
|
| 606 |
+
"lstrip": true,
|
| 607 |
+
"normalized": false,
|
| 608 |
+
"rstrip": true,
|
| 609 |
+
"single_word": false,
|
| 610 |
+
"special": true
|
| 611 |
+
},
|
| 612 |
+
"36073": {
|
| 613 |
+
"content": "<extra_id_22>",
|
| 614 |
+
"lstrip": true,
|
| 615 |
+
"normalized": false,
|
| 616 |
+
"rstrip": true,
|
| 617 |
+
"single_word": false,
|
| 618 |
+
"special": true
|
| 619 |
+
},
|
| 620 |
+
"36074": {
|
| 621 |
+
"content": "<extra_id_21>",
|
| 622 |
+
"lstrip": true,
|
| 623 |
+
"normalized": false,
|
| 624 |
+
"rstrip": true,
|
| 625 |
+
"single_word": false,
|
| 626 |
+
"special": true
|
| 627 |
+
},
|
| 628 |
+
"36075": {
|
| 629 |
+
"content": "<extra_id_20>",
|
| 630 |
+
"lstrip": true,
|
| 631 |
+
"normalized": false,
|
| 632 |
+
"rstrip": true,
|
| 633 |
+
"single_word": false,
|
| 634 |
+
"special": true
|
| 635 |
+
},
|
| 636 |
+
"36076": {
|
| 637 |
+
"content": "<extra_id_19>",
|
| 638 |
+
"lstrip": true,
|
| 639 |
+
"normalized": false,
|
| 640 |
+
"rstrip": true,
|
| 641 |
+
"single_word": false,
|
| 642 |
+
"special": true
|
| 643 |
+
},
|
| 644 |
+
"36077": {
|
| 645 |
+
"content": "<extra_id_18>",
|
| 646 |
+
"lstrip": true,
|
| 647 |
+
"normalized": false,
|
| 648 |
+
"rstrip": true,
|
| 649 |
+
"single_word": false,
|
| 650 |
+
"special": true
|
| 651 |
+
},
|
| 652 |
+
"36078": {
|
| 653 |
+
"content": "<extra_id_17>",
|
| 654 |
+
"lstrip": true,
|
| 655 |
+
"normalized": false,
|
| 656 |
+
"rstrip": true,
|
| 657 |
+
"single_word": false,
|
| 658 |
+
"special": true
|
| 659 |
+
},
|
| 660 |
+
"36079": {
|
| 661 |
+
"content": "<extra_id_16>",
|
| 662 |
+
"lstrip": true,
|
| 663 |
+
"normalized": false,
|
| 664 |
+
"rstrip": true,
|
| 665 |
+
"single_word": false,
|
| 666 |
+
"special": true
|
| 667 |
+
},
|
| 668 |
+
"36080": {
|
| 669 |
+
"content": "<extra_id_15>",
|
| 670 |
+
"lstrip": true,
|
| 671 |
+
"normalized": false,
|
| 672 |
+
"rstrip": true,
|
| 673 |
+
"single_word": false,
|
| 674 |
+
"special": true
|
| 675 |
+
},
|
| 676 |
+
"36081": {
|
| 677 |
+
"content": "<extra_id_14>",
|
| 678 |
+
"lstrip": true,
|
| 679 |
+
"normalized": false,
|
| 680 |
+
"rstrip": true,
|
| 681 |
+
"single_word": false,
|
| 682 |
+
"special": true
|
| 683 |
+
},
|
| 684 |
+
"36082": {
|
| 685 |
+
"content": "<extra_id_13>",
|
| 686 |
+
"lstrip": true,
|
| 687 |
+
"normalized": false,
|
| 688 |
+
"rstrip": true,
|
| 689 |
+
"single_word": false,
|
| 690 |
+
"special": true
|
| 691 |
+
},
|
| 692 |
+
"36083": {
|
| 693 |
+
"content": "<extra_id_12>",
|
| 694 |
+
"lstrip": true,
|
| 695 |
+
"normalized": false,
|
| 696 |
+
"rstrip": true,
|
| 697 |
+
"single_word": false,
|
| 698 |
+
"special": true
|
| 699 |
+
},
|
| 700 |
+
"36084": {
|
| 701 |
+
"content": "<extra_id_11>",
|
| 702 |
+
"lstrip": true,
|
| 703 |
+
"normalized": false,
|
| 704 |
+
"rstrip": true,
|
| 705 |
+
"single_word": false,
|
| 706 |
+
"special": true
|
| 707 |
+
},
|
| 708 |
+
"36085": {
|
| 709 |
+
"content": "<extra_id_10>",
|
| 710 |
+
"lstrip": true,
|
| 711 |
+
"normalized": false,
|
| 712 |
+
"rstrip": true,
|
| 713 |
+
"single_word": false,
|
| 714 |
+
"special": true
|
| 715 |
+
},
|
| 716 |
+
"36086": {
|
| 717 |
+
"content": "<extra_id_9>",
|
| 718 |
+
"lstrip": true,
|
| 719 |
+
"normalized": false,
|
| 720 |
+
"rstrip": true,
|
| 721 |
+
"single_word": false,
|
| 722 |
+
"special": true
|
| 723 |
+
},
|
| 724 |
+
"36087": {
|
| 725 |
+
"content": "<extra_id_8>",
|
| 726 |
+
"lstrip": true,
|
| 727 |
+
"normalized": false,
|
| 728 |
+
"rstrip": true,
|
| 729 |
+
"single_word": false,
|
| 730 |
+
"special": true
|
| 731 |
+
},
|
| 732 |
+
"36088": {
|
| 733 |
+
"content": "<extra_id_7>",
|
| 734 |
+
"lstrip": true,
|
| 735 |
+
"normalized": false,
|
| 736 |
+
"rstrip": true,
|
| 737 |
+
"single_word": false,
|
| 738 |
+
"special": true
|
| 739 |
+
},
|
| 740 |
+
"36089": {
|
| 741 |
+
"content": "<extra_id_6>",
|
| 742 |
+
"lstrip": true,
|
| 743 |
+
"normalized": false,
|
| 744 |
+
"rstrip": true,
|
| 745 |
+
"single_word": false,
|
| 746 |
+
"special": true
|
| 747 |
+
},
|
| 748 |
+
"36090": {
|
| 749 |
+
"content": "<extra_id_5>",
|
| 750 |
+
"lstrip": true,
|
| 751 |
+
"normalized": false,
|
| 752 |
+
"rstrip": true,
|
| 753 |
+
"single_word": false,
|
| 754 |
+
"special": true
|
| 755 |
+
},
|
| 756 |
+
"36091": {
|
| 757 |
+
"content": "<extra_id_4>",
|
| 758 |
+
"lstrip": true,
|
| 759 |
+
"normalized": false,
|
| 760 |
+
"rstrip": true,
|
| 761 |
+
"single_word": false,
|
| 762 |
+
"special": true
|
| 763 |
+
},
|
| 764 |
+
"36092": {
|
| 765 |
+
"content": "<extra_id_3>",
|
| 766 |
+
"lstrip": true,
|
| 767 |
+
"normalized": false,
|
| 768 |
+
"rstrip": true,
|
| 769 |
+
"single_word": false,
|
| 770 |
+
"special": true
|
| 771 |
+
},
|
| 772 |
+
"36093": {
|
| 773 |
+
"content": "<extra_id_2>",
|
| 774 |
+
"lstrip": true,
|
| 775 |
+
"normalized": false,
|
| 776 |
+
"rstrip": true,
|
| 777 |
+
"single_word": false,
|
| 778 |
+
"special": true
|
| 779 |
+
},
|
| 780 |
+
"36094": {
|
| 781 |
+
"content": "<extra_id_1>",
|
| 782 |
+
"lstrip": true,
|
| 783 |
+
"normalized": false,
|
| 784 |
+
"rstrip": true,
|
| 785 |
+
"single_word": false,
|
| 786 |
+
"special": true
|
| 787 |
+
},
|
| 788 |
+
"36095": {
|
| 789 |
+
"content": "<extra_id_0>",
|
| 790 |
+
"lstrip": true,
|
| 791 |
+
"normalized": false,
|
| 792 |
+
"rstrip": true,
|
| 793 |
+
"single_word": false,
|
| 794 |
+
"special": true
|
| 795 |
+
},
|
| 796 |
+
"36096": {
|
| 797 |
+
"content": "SEM_5",
|
| 798 |
+
"lstrip": false,
|
| 799 |
+
"normalized": false,
|
| 800 |
+
"rstrip": false,
|
| 801 |
+
"single_word": false,
|
| 802 |
+
"special": true
|
| 803 |
+
},
|
| 804 |
+
"36097": {
|
| 805 |
+
"content": "SEM_10",
|
| 806 |
+
"lstrip": false,
|
| 807 |
+
"normalized": false,
|
| 808 |
+
"rstrip": false,
|
| 809 |
+
"single_word": false,
|
| 810 |
+
"special": true
|
| 811 |
+
},
|
| 812 |
+
"36098": {
|
| 813 |
+
"content": "SEM_15",
|
| 814 |
+
"lstrip": false,
|
| 815 |
+
"normalized": false,
|
| 816 |
+
"rstrip": false,
|
| 817 |
+
"single_word": false,
|
| 818 |
+
"special": true
|
| 819 |
+
},
|
| 820 |
+
"36099": {
|
| 821 |
+
"content": "SEM_20",
|
| 822 |
+
"lstrip": false,
|
| 823 |
+
"normalized": false,
|
| 824 |
+
"rstrip": false,
|
| 825 |
+
"single_word": false,
|
| 826 |
+
"special": true
|
| 827 |
+
},
|
| 828 |
+
"36100": {
|
| 829 |
+
"content": "SEM_25",
|
| 830 |
+
"lstrip": false,
|
| 831 |
+
"normalized": false,
|
| 832 |
+
"rstrip": false,
|
| 833 |
+
"single_word": false,
|
| 834 |
+
"special": true
|
| 835 |
+
},
|
| 836 |
+
"36101": {
|
| 837 |
+
"content": "SEM_30",
|
| 838 |
+
"lstrip": false,
|
| 839 |
+
"normalized": false,
|
| 840 |
+
"rstrip": false,
|
| 841 |
+
"single_word": false,
|
| 842 |
+
"special": true
|
| 843 |
+
},
|
| 844 |
+
"36102": {
|
| 845 |
+
"content": "SEM_35",
|
| 846 |
+
"lstrip": false,
|
| 847 |
+
"normalized": false,
|
| 848 |
+
"rstrip": false,
|
| 849 |
+
"single_word": false,
|
| 850 |
+
"special": true
|
| 851 |
+
},
|
| 852 |
+
"36103": {
|
| 853 |
+
"content": "SEM_40",
|
| 854 |
+
"lstrip": false,
|
| 855 |
+
"normalized": false,
|
| 856 |
+
"rstrip": false,
|
| 857 |
+
"single_word": false,
|
| 858 |
+
"special": true
|
| 859 |
+
},
|
| 860 |
+
"36104": {
|
| 861 |
+
"content": "SEM_45",
|
| 862 |
+
"lstrip": false,
|
| 863 |
+
"normalized": false,
|
| 864 |
+
"rstrip": false,
|
| 865 |
+
"single_word": false,
|
| 866 |
+
"special": true
|
| 867 |
+
},
|
| 868 |
+
"36105": {
|
| 869 |
+
"content": "SEM_50",
|
| 870 |
+
"lstrip": false,
|
| 871 |
+
"normalized": false,
|
| 872 |
+
"rstrip": false,
|
| 873 |
+
"single_word": false,
|
| 874 |
+
"special": true
|
| 875 |
+
},
|
| 876 |
+
"36106": {
|
| 877 |
+
"content": "SEM_55",
|
| 878 |
+
"lstrip": false,
|
| 879 |
+
"normalized": false,
|
| 880 |
+
"rstrip": false,
|
| 881 |
+
"single_word": false,
|
| 882 |
+
"special": true
|
| 883 |
+
},
|
| 884 |
+
"36107": {
|
| 885 |
+
"content": "SEM_60",
|
| 886 |
+
"lstrip": false,
|
| 887 |
+
"normalized": false,
|
| 888 |
+
"rstrip": false,
|
| 889 |
+
"single_word": false,
|
| 890 |
+
"special": true
|
| 891 |
+
},
|
| 892 |
+
"36108": {
|
| 893 |
+
"content": "SEM_65",
|
| 894 |
+
"lstrip": false,
|
| 895 |
+
"normalized": false,
|
| 896 |
+
"rstrip": false,
|
| 897 |
+
"single_word": false,
|
| 898 |
+
"special": true
|
| 899 |
+
},
|
| 900 |
+
"36109": {
|
| 901 |
+
"content": "SEM_70",
|
| 902 |
+
"lstrip": false,
|
| 903 |
+
"normalized": false,
|
| 904 |
+
"rstrip": false,
|
| 905 |
+
"single_word": false,
|
| 906 |
+
"special": true
|
| 907 |
+
},
|
| 908 |
+
"36110": {
|
| 909 |
+
"content": "SEM_75",
|
| 910 |
+
"lstrip": false,
|
| 911 |
+
"normalized": false,
|
| 912 |
+
"rstrip": false,
|
| 913 |
+
"single_word": false,
|
| 914 |
+
"special": true
|
| 915 |
+
},
|
| 916 |
+
"36111": {
|
| 917 |
+
"content": "SEM_80",
|
| 918 |
+
"lstrip": false,
|
| 919 |
+
"normalized": false,
|
| 920 |
+
"rstrip": false,
|
| 921 |
+
"single_word": false,
|
| 922 |
+
"special": true
|
| 923 |
+
},
|
| 924 |
+
"36112": {
|
| 925 |
+
"content": "SEM_85",
|
| 926 |
+
"lstrip": false,
|
| 927 |
+
"normalized": false,
|
| 928 |
+
"rstrip": false,
|
| 929 |
+
"single_word": false,
|
| 930 |
+
"special": true
|
| 931 |
+
},
|
| 932 |
+
"36113": {
|
| 933 |
+
"content": "SEM_90",
|
| 934 |
+
"lstrip": false,
|
| 935 |
+
"normalized": false,
|
| 936 |
+
"rstrip": false,
|
| 937 |
+
"single_word": false,
|
| 938 |
+
"special": true
|
| 939 |
+
},
|
| 940 |
+
"36114": {
|
| 941 |
+
"content": "SEM_95",
|
| 942 |
+
"lstrip": false,
|
| 943 |
+
"normalized": false,
|
| 944 |
+
"rstrip": false,
|
| 945 |
+
"single_word": false,
|
| 946 |
+
"special": true
|
| 947 |
+
},
|
| 948 |
+
"36115": {
|
| 949 |
+
"content": "SYN_5",
|
| 950 |
+
"lstrip": false,
|
| 951 |
+
"normalized": false,
|
| 952 |
+
"rstrip": false,
|
| 953 |
+
"single_word": false,
|
| 954 |
+
"special": true
|
| 955 |
+
},
|
| 956 |
+
"36116": {
|
| 957 |
+
"content": "SYN_10",
|
| 958 |
+
"lstrip": false,
|
| 959 |
+
"normalized": false,
|
| 960 |
+
"rstrip": false,
|
| 961 |
+
"single_word": false,
|
| 962 |
+
"special": true
|
| 963 |
+
},
|
| 964 |
+
"36117": {
|
| 965 |
+
"content": "SYN_15",
|
| 966 |
+
"lstrip": false,
|
| 967 |
+
"normalized": false,
|
| 968 |
+
"rstrip": false,
|
| 969 |
+
"single_word": false,
|
| 970 |
+
"special": true
|
| 971 |
+
},
|
| 972 |
+
"36118": {
|
| 973 |
+
"content": "SYN_20",
|
| 974 |
+
"lstrip": false,
|
| 975 |
+
"normalized": false,
|
| 976 |
+
"rstrip": false,
|
| 977 |
+
"single_word": false,
|
| 978 |
+
"special": true
|
| 979 |
+
},
|
| 980 |
+
"36119": {
|
| 981 |
+
"content": "SYN_25",
|
| 982 |
+
"lstrip": false,
|
| 983 |
+
"normalized": false,
|
| 984 |
+
"rstrip": false,
|
| 985 |
+
"single_word": false,
|
| 986 |
+
"special": true
|
| 987 |
+
},
|
| 988 |
+
"36120": {
|
| 989 |
+
"content": "SYN_30",
|
| 990 |
+
"lstrip": false,
|
| 991 |
+
"normalized": false,
|
| 992 |
+
"rstrip": false,
|
| 993 |
+
"single_word": false,
|
| 994 |
+
"special": true
|
| 995 |
+
},
|
| 996 |
+
"36121": {
|
| 997 |
+
"content": "SYN_35",
|
| 998 |
+
"lstrip": false,
|
| 999 |
+
"normalized": false,
|
| 1000 |
+
"rstrip": false,
|
| 1001 |
+
"single_word": false,
|
| 1002 |
+
"special": true
|
| 1003 |
+
},
|
| 1004 |
+
"36122": {
|
| 1005 |
+
"content": "SYN_40",
|
| 1006 |
+
"lstrip": false,
|
| 1007 |
+
"normalized": false,
|
| 1008 |
+
"rstrip": false,
|
| 1009 |
+
"single_word": false,
|
| 1010 |
+
"special": true
|
| 1011 |
+
},
|
| 1012 |
+
"36123": {
|
| 1013 |
+
"content": "SYN_45",
|
| 1014 |
+
"lstrip": false,
|
| 1015 |
+
"normalized": false,
|
| 1016 |
+
"rstrip": false,
|
| 1017 |
+
"single_word": false,
|
| 1018 |
+
"special": true
|
| 1019 |
+
},
|
| 1020 |
+
"36124": {
|
| 1021 |
+
"content": "SYN_50",
|
| 1022 |
+
"lstrip": false,
|
| 1023 |
+
"normalized": false,
|
| 1024 |
+
"rstrip": false,
|
| 1025 |
+
"single_word": false,
|
| 1026 |
+
"special": true
|
| 1027 |
+
},
|
| 1028 |
+
"36125": {
|
| 1029 |
+
"content": "SYN_55",
|
| 1030 |
+
"lstrip": false,
|
| 1031 |
+
"normalized": false,
|
| 1032 |
+
"rstrip": false,
|
| 1033 |
+
"single_word": false,
|
| 1034 |
+
"special": true
|
| 1035 |
+
},
|
| 1036 |
+
"36126": {
|
| 1037 |
+
"content": "SYN_60",
|
| 1038 |
+
"lstrip": false,
|
| 1039 |
+
"normalized": false,
|
| 1040 |
+
"rstrip": false,
|
| 1041 |
+
"single_word": false,
|
| 1042 |
+
"special": true
|
| 1043 |
+
},
|
| 1044 |
+
"36127": {
|
| 1045 |
+
"content": "SYN_65",
|
| 1046 |
+
"lstrip": false,
|
| 1047 |
+
"normalized": false,
|
| 1048 |
+
"rstrip": false,
|
| 1049 |
+
"single_word": false,
|
| 1050 |
+
"special": true
|
| 1051 |
+
},
|
| 1052 |
+
"36128": {
|
| 1053 |
+
"content": "SYN_70",
|
| 1054 |
+
"lstrip": false,
|
| 1055 |
+
"normalized": false,
|
| 1056 |
+
"rstrip": false,
|
| 1057 |
+
"single_word": false,
|
| 1058 |
+
"special": true
|
| 1059 |
+
},
|
| 1060 |
+
"36129": {
|
| 1061 |
+
"content": "SYN_75",
|
| 1062 |
+
"lstrip": false,
|
| 1063 |
+
"normalized": false,
|
| 1064 |
+
"rstrip": false,
|
| 1065 |
+
"single_word": false,
|
| 1066 |
+
"special": true
|
| 1067 |
+
},
|
| 1068 |
+
"36130": {
|
| 1069 |
+
"content": "SYN_80",
|
| 1070 |
+
"lstrip": false,
|
| 1071 |
+
"normalized": false,
|
| 1072 |
+
"rstrip": false,
|
| 1073 |
+
"single_word": false,
|
| 1074 |
+
"special": true
|
| 1075 |
+
},
|
| 1076 |
+
"36131": {
|
| 1077 |
+
"content": "SYN_85",
|
| 1078 |
+
"lstrip": false,
|
| 1079 |
+
"normalized": false,
|
| 1080 |
+
"rstrip": false,
|
| 1081 |
+
"single_word": false,
|
| 1082 |
+
"special": true
|
| 1083 |
+
},
|
| 1084 |
+
"36132": {
|
| 1085 |
+
"content": "SYN_90",
|
| 1086 |
+
"lstrip": false,
|
| 1087 |
+
"normalized": false,
|
| 1088 |
+
"rstrip": false,
|
| 1089 |
+
"single_word": false,
|
| 1090 |
+
"special": true
|
| 1091 |
+
},
|
| 1092 |
+
"36133": {
|
| 1093 |
+
"content": "SYN_95",
|
| 1094 |
+
"lstrip": false,
|
| 1095 |
+
"normalized": false,
|
| 1096 |
+
"rstrip": false,
|
| 1097 |
+
"single_word": false,
|
| 1098 |
+
"special": true
|
| 1099 |
+
},
|
| 1100 |
+
"36134": {
|
| 1101 |
+
"content": "LEX_5",
|
| 1102 |
+
"lstrip": false,
|
| 1103 |
+
"normalized": false,
|
| 1104 |
+
"rstrip": false,
|
| 1105 |
+
"single_word": false,
|
| 1106 |
+
"special": true
|
| 1107 |
+
},
|
| 1108 |
+
"36135": {
|
| 1109 |
+
"content": "LEX_10",
|
| 1110 |
+
"lstrip": false,
|
| 1111 |
+
"normalized": false,
|
| 1112 |
+
"rstrip": false,
|
| 1113 |
+
"single_word": false,
|
| 1114 |
+
"special": true
|
| 1115 |
+
},
|
| 1116 |
+
"36136": {
|
| 1117 |
+
"content": "LEX_15",
|
| 1118 |
+
"lstrip": false,
|
| 1119 |
+
"normalized": false,
|
| 1120 |
+
"rstrip": false,
|
| 1121 |
+
"single_word": false,
|
| 1122 |
+
"special": true
|
| 1123 |
+
},
|
| 1124 |
+
"36137": {
|
| 1125 |
+
"content": "LEX_20",
|
| 1126 |
+
"lstrip": false,
|
| 1127 |
+
"normalized": false,
|
| 1128 |
+
"rstrip": false,
|
| 1129 |
+
"single_word": false,
|
| 1130 |
+
"special": true
|
| 1131 |
+
},
|
| 1132 |
+
"36138": {
|
| 1133 |
+
"content": "LEX_25",
|
| 1134 |
+
"lstrip": false,
|
| 1135 |
+
"normalized": false,
|
| 1136 |
+
"rstrip": false,
|
| 1137 |
+
"single_word": false,
|
| 1138 |
+
"special": true
|
| 1139 |
+
},
|
| 1140 |
+
"36139": {
|
| 1141 |
+
"content": "LEX_30",
|
| 1142 |
+
"lstrip": false,
|
| 1143 |
+
"normalized": false,
|
| 1144 |
+
"rstrip": false,
|
| 1145 |
+
"single_word": false,
|
| 1146 |
+
"special": true
|
| 1147 |
+
},
|
| 1148 |
+
"36140": {
|
| 1149 |
+
"content": "LEX_35",
|
| 1150 |
+
"lstrip": false,
|
| 1151 |
+
"normalized": false,
|
| 1152 |
+
"rstrip": false,
|
| 1153 |
+
"single_word": false,
|
| 1154 |
+
"special": true
|
| 1155 |
+
},
|
| 1156 |
+
"36141": {
|
| 1157 |
+
"content": "LEX_40",
|
| 1158 |
+
"lstrip": false,
|
| 1159 |
+
"normalized": false,
|
| 1160 |
+
"rstrip": false,
|
| 1161 |
+
"single_word": false,
|
| 1162 |
+
"special": true
|
| 1163 |
+
},
|
| 1164 |
+
"36142": {
|
| 1165 |
+
"content": "LEX_45",
|
| 1166 |
+
"lstrip": false,
|
| 1167 |
+
"normalized": false,
|
| 1168 |
+
"rstrip": false,
|
| 1169 |
+
"single_word": false,
|
| 1170 |
+
"special": true
|
| 1171 |
+
},
|
| 1172 |
+
"36143": {
|
| 1173 |
+
"content": "LEX_50",
|
| 1174 |
+
"lstrip": false,
|
| 1175 |
+
"normalized": false,
|
| 1176 |
+
"rstrip": false,
|
| 1177 |
+
"single_word": false,
|
| 1178 |
+
"special": true
|
| 1179 |
+
},
|
| 1180 |
+
"36144": {
|
| 1181 |
+
"content": "LEX_55",
|
| 1182 |
+
"lstrip": false,
|
| 1183 |
+
"normalized": false,
|
| 1184 |
+
"rstrip": false,
|
| 1185 |
+
"single_word": false,
|
| 1186 |
+
"special": true
|
| 1187 |
+
},
|
| 1188 |
+
"36145": {
|
| 1189 |
+
"content": "LEX_60",
|
| 1190 |
+
"lstrip": false,
|
| 1191 |
+
"normalized": false,
|
| 1192 |
+
"rstrip": false,
|
| 1193 |
+
"single_word": false,
|
| 1194 |
+
"special": true
|
| 1195 |
+
},
|
| 1196 |
+
"36146": {
|
| 1197 |
+
"content": "LEX_65",
|
| 1198 |
+
"lstrip": false,
|
| 1199 |
+
"normalized": false,
|
| 1200 |
+
"rstrip": false,
|
| 1201 |
+
"single_word": false,
|
| 1202 |
+
"special": true
|
| 1203 |
+
},
|
| 1204 |
+
"36147": {
|
| 1205 |
+
"content": "LEX_70",
|
| 1206 |
+
"lstrip": false,
|
| 1207 |
+
"normalized": false,
|
| 1208 |
+
"rstrip": false,
|
| 1209 |
+
"single_word": false,
|
| 1210 |
+
"special": true
|
| 1211 |
+
},
|
| 1212 |
+
"36148": {
|
| 1213 |
+
"content": "LEX_75",
|
| 1214 |
+
"lstrip": false,
|
| 1215 |
+
"normalized": false,
|
| 1216 |
+
"rstrip": false,
|
| 1217 |
+
"single_word": false,
|
| 1218 |
+
"special": true
|
| 1219 |
+
},
|
| 1220 |
+
"36149": {
|
| 1221 |
+
"content": "LEX_80",
|
| 1222 |
+
"lstrip": false,
|
| 1223 |
+
"normalized": false,
|
| 1224 |
+
"rstrip": false,
|
| 1225 |
+
"single_word": false,
|
| 1226 |
+
"special": true
|
| 1227 |
+
},
|
| 1228 |
+
"36150": {
|
| 1229 |
+
"content": "LEX_85",
|
| 1230 |
+
"lstrip": false,
|
| 1231 |
+
"normalized": false,
|
| 1232 |
+
"rstrip": false,
|
| 1233 |
+
"single_word": false,
|
| 1234 |
+
"special": true
|
| 1235 |
+
},
|
| 1236 |
+
"36151": {
|
| 1237 |
+
"content": "LEX_90",
|
| 1238 |
+
"lstrip": false,
|
| 1239 |
+
"normalized": false,
|
| 1240 |
+
"rstrip": false,
|
| 1241 |
+
"single_word": false,
|
| 1242 |
+
"special": true
|
| 1243 |
+
},
|
| 1244 |
+
"36152": {
|
| 1245 |
+
"content": "LEX_95",
|
| 1246 |
+
"lstrip": false,
|
| 1247 |
+
"normalized": false,
|
| 1248 |
+
"rstrip": false,
|
| 1249 |
+
"single_word": false,
|
| 1250 |
+
"special": true
|
| 1251 |
+
}
|
| 1252 |
+
},
|
| 1253 |
+
"additional_special_tokens": [
|
| 1254 |
+
"SEM_5",
|
| 1255 |
+
"SEM_10",
|
| 1256 |
+
"SEM_15",
|
| 1257 |
+
"SEM_20",
|
| 1258 |
+
"SEM_25",
|
| 1259 |
+
"SEM_30",
|
| 1260 |
+
"SEM_35",
|
| 1261 |
+
"SEM_40",
|
| 1262 |
+
"SEM_45",
|
| 1263 |
+
"SEM_50",
|
| 1264 |
+
"SEM_55",
|
| 1265 |
+
"SEM_60",
|
| 1266 |
+
"SEM_65",
|
| 1267 |
+
"SEM_70",
|
| 1268 |
+
"SEM_75",
|
| 1269 |
+
"SEM_80",
|
| 1270 |
+
"SEM_85",
|
| 1271 |
+
"SEM_90",
|
| 1272 |
+
"SEM_95",
|
| 1273 |
+
"SYN_5",
|
| 1274 |
+
"SYN_10",
|
| 1275 |
+
"SYN_15",
|
| 1276 |
+
"SYN_20",
|
| 1277 |
+
"SYN_25",
|
| 1278 |
+
"SYN_30",
|
| 1279 |
+
"SYN_35",
|
| 1280 |
+
"SYN_40",
|
| 1281 |
+
"SYN_45",
|
| 1282 |
+
"SYN_50",
|
| 1283 |
+
"SYN_55",
|
| 1284 |
+
"SYN_60",
|
| 1285 |
+
"SYN_65",
|
| 1286 |
+
"SYN_70",
|
| 1287 |
+
"SYN_75",
|
| 1288 |
+
"SYN_80",
|
| 1289 |
+
"SYN_85",
|
| 1290 |
+
"SYN_90",
|
| 1291 |
+
"SYN_95",
|
| 1292 |
+
"LEX_5",
|
| 1293 |
+
"LEX_10",
|
| 1294 |
+
"LEX_15",
|
| 1295 |
+
"LEX_20",
|
| 1296 |
+
"LEX_25",
|
| 1297 |
+
"LEX_30",
|
| 1298 |
+
"LEX_35",
|
| 1299 |
+
"LEX_40",
|
| 1300 |
+
"LEX_45",
|
| 1301 |
+
"LEX_50",
|
| 1302 |
+
"LEX_55",
|
| 1303 |
+
"LEX_60",
|
| 1304 |
+
"LEX_65",
|
| 1305 |
+
"LEX_70",
|
| 1306 |
+
"LEX_75",
|
| 1307 |
+
"LEX_80",
|
| 1308 |
+
"LEX_85",
|
| 1309 |
+
"LEX_90",
|
| 1310 |
+
"LEX_95"
|
| 1311 |
+
],
|
| 1312 |
+
"clean_up_tokenization_spaces": true,
|
| 1313 |
+
"eos_token": "</s>",
|
| 1314 |
+
"extra_ids": 96,
|
| 1315 |
+
"legacy": true,
|
| 1316 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 1317 |
+
"pad_token": "<pad>",
|
| 1318 |
+
"sp_model_kwargs": {},
|
| 1319 |
+
"tokenizer_class": "T5Tokenizer",
|
| 1320 |
+
"unk_token": "<unk>"
|
| 1321 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da136a229f527c2e426c29a9ee3356c3be55e8201cce6ba30c355ca198dd7db5
|
| 3 |
+
size 5176
|