model added
Browse files- added_tokens.json +127 -0
- config.json +341 -0
- generation_config.json +8 -0
- model.safetensors +3 -0
- preprocessor_config.json +35 -0
- special_tokens_map.json +150 -0
- tokenizer_config.json +1163 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,127 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<extra_id_0>": 259,
|
| 3 |
+
"<extra_id_100>": 359,
|
| 4 |
+
"<extra_id_101>": 360,
|
| 5 |
+
"<extra_id_102>": 361,
|
| 6 |
+
"<extra_id_103>": 362,
|
| 7 |
+
"<extra_id_104>": 363,
|
| 8 |
+
"<extra_id_105>": 364,
|
| 9 |
+
"<extra_id_106>": 365,
|
| 10 |
+
"<extra_id_107>": 366,
|
| 11 |
+
"<extra_id_108>": 367,
|
| 12 |
+
"<extra_id_109>": 368,
|
| 13 |
+
"<extra_id_10>": 269,
|
| 14 |
+
"<extra_id_110>": 369,
|
| 15 |
+
"<extra_id_111>": 370,
|
| 16 |
+
"<extra_id_112>": 371,
|
| 17 |
+
"<extra_id_113>": 372,
|
| 18 |
+
"<extra_id_114>": 373,
|
| 19 |
+
"<extra_id_115>": 374,
|
| 20 |
+
"<extra_id_116>": 375,
|
| 21 |
+
"<extra_id_117>": 376,
|
| 22 |
+
"<extra_id_118>": 377,
|
| 23 |
+
"<extra_id_119>": 378,
|
| 24 |
+
"<extra_id_11>": 270,
|
| 25 |
+
"<extra_id_120>": 379,
|
| 26 |
+
"<extra_id_121>": 380,
|
| 27 |
+
"<extra_id_122>": 381,
|
| 28 |
+
"<extra_id_123>": 382,
|
| 29 |
+
"<extra_id_124>": 383,
|
| 30 |
+
"<extra_id_12>": 271,
|
| 31 |
+
"<extra_id_13>": 272,
|
| 32 |
+
"<extra_id_14>": 273,
|
| 33 |
+
"<extra_id_15>": 274,
|
| 34 |
+
"<extra_id_16>": 275,
|
| 35 |
+
"<extra_id_17>": 276,
|
| 36 |
+
"<extra_id_18>": 277,
|
| 37 |
+
"<extra_id_19>": 278,
|
| 38 |
+
"<extra_id_1>": 260,
|
| 39 |
+
"<extra_id_20>": 279,
|
| 40 |
+
"<extra_id_21>": 280,
|
| 41 |
+
"<extra_id_22>": 281,
|
| 42 |
+
"<extra_id_23>": 282,
|
| 43 |
+
"<extra_id_24>": 283,
|
| 44 |
+
"<extra_id_25>": 284,
|
| 45 |
+
"<extra_id_26>": 285,
|
| 46 |
+
"<extra_id_27>": 286,
|
| 47 |
+
"<extra_id_28>": 287,
|
| 48 |
+
"<extra_id_29>": 288,
|
| 49 |
+
"<extra_id_2>": 261,
|
| 50 |
+
"<extra_id_30>": 289,
|
| 51 |
+
"<extra_id_31>": 290,
|
| 52 |
+
"<extra_id_32>": 291,
|
| 53 |
+
"<extra_id_33>": 292,
|
| 54 |
+
"<extra_id_34>": 293,
|
| 55 |
+
"<extra_id_35>": 294,
|
| 56 |
+
"<extra_id_36>": 295,
|
| 57 |
+
"<extra_id_37>": 296,
|
| 58 |
+
"<extra_id_38>": 297,
|
| 59 |
+
"<extra_id_39>": 298,
|
| 60 |
+
"<extra_id_3>": 262,
|
| 61 |
+
"<extra_id_40>": 299,
|
| 62 |
+
"<extra_id_41>": 300,
|
| 63 |
+
"<extra_id_42>": 301,
|
| 64 |
+
"<extra_id_43>": 302,
|
| 65 |
+
"<extra_id_44>": 303,
|
| 66 |
+
"<extra_id_45>": 304,
|
| 67 |
+
"<extra_id_46>": 305,
|
| 68 |
+
"<extra_id_47>": 306,
|
| 69 |
+
"<extra_id_48>": 307,
|
| 70 |
+
"<extra_id_49>": 308,
|
| 71 |
+
"<extra_id_4>": 263,
|
| 72 |
+
"<extra_id_50>": 309,
|
| 73 |
+
"<extra_id_51>": 310,
|
| 74 |
+
"<extra_id_52>": 311,
|
| 75 |
+
"<extra_id_53>": 312,
|
| 76 |
+
"<extra_id_54>": 313,
|
| 77 |
+
"<extra_id_55>": 314,
|
| 78 |
+
"<extra_id_56>": 315,
|
| 79 |
+
"<extra_id_57>": 316,
|
| 80 |
+
"<extra_id_58>": 317,
|
| 81 |
+
"<extra_id_59>": 318,
|
| 82 |
+
"<extra_id_5>": 264,
|
| 83 |
+
"<extra_id_60>": 319,
|
| 84 |
+
"<extra_id_61>": 320,
|
| 85 |
+
"<extra_id_62>": 321,
|
| 86 |
+
"<extra_id_63>": 322,
|
| 87 |
+
"<extra_id_64>": 323,
|
| 88 |
+
"<extra_id_65>": 324,
|
| 89 |
+
"<extra_id_66>": 325,
|
| 90 |
+
"<extra_id_67>": 326,
|
| 91 |
+
"<extra_id_68>": 327,
|
| 92 |
+
"<extra_id_69>": 328,
|
| 93 |
+
"<extra_id_6>": 265,
|
| 94 |
+
"<extra_id_70>": 329,
|
| 95 |
+
"<extra_id_71>": 330,
|
| 96 |
+
"<extra_id_72>": 331,
|
| 97 |
+
"<extra_id_73>": 332,
|
| 98 |
+
"<extra_id_74>": 333,
|
| 99 |
+
"<extra_id_75>": 334,
|
| 100 |
+
"<extra_id_76>": 335,
|
| 101 |
+
"<extra_id_77>": 336,
|
| 102 |
+
"<extra_id_78>": 337,
|
| 103 |
+
"<extra_id_79>": 338,
|
| 104 |
+
"<extra_id_7>": 266,
|
| 105 |
+
"<extra_id_80>": 339,
|
| 106 |
+
"<extra_id_81>": 340,
|
| 107 |
+
"<extra_id_82>": 341,
|
| 108 |
+
"<extra_id_83>": 342,
|
| 109 |
+
"<extra_id_84>": 343,
|
| 110 |
+
"<extra_id_85>": 344,
|
| 111 |
+
"<extra_id_86>": 345,
|
| 112 |
+
"<extra_id_87>": 346,
|
| 113 |
+
"<extra_id_88>": 347,
|
| 114 |
+
"<extra_id_89>": 348,
|
| 115 |
+
"<extra_id_8>": 267,
|
| 116 |
+
"<extra_id_90>": 349,
|
| 117 |
+
"<extra_id_91>": 350,
|
| 118 |
+
"<extra_id_92>": 351,
|
| 119 |
+
"<extra_id_93>": 352,
|
| 120 |
+
"<extra_id_94>": 353,
|
| 121 |
+
"<extra_id_95>": 354,
|
| 122 |
+
"<extra_id_96>": 355,
|
| 123 |
+
"<extra_id_97>": 356,
|
| 124 |
+
"<extra_id_98>": 357,
|
| 125 |
+
"<extra_id_99>": 358,
|
| 126 |
+
"<extra_id_9>": 268
|
| 127 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,341 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/content/rec_model",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"OCREncoderDecoderModel"
|
| 5 |
+
],
|
| 6 |
+
"decoder": {
|
| 7 |
+
"_name_or_path": "",
|
| 8 |
+
"add_cross_attention": false,
|
| 9 |
+
"architectures": null,
|
| 10 |
+
"attention_bias": false,
|
| 11 |
+
"attention_dropout": 0.0,
|
| 12 |
+
"attention_window_size": 16,
|
| 13 |
+
"aux_heads": 0,
|
| 14 |
+
"bad_words_ids": null,
|
| 15 |
+
"begin_suppress_tokens": null,
|
| 16 |
+
"block_types": [
|
| 17 |
+
"attention"
|
| 18 |
+
],
|
| 19 |
+
"bos_token_id": 1,
|
| 20 |
+
"causal": true,
|
| 21 |
+
"chunk_size_feed_forward": 0,
|
| 22 |
+
"conv1d_width": 4,
|
| 23 |
+
"cross_attention_hidden_size": null,
|
| 24 |
+
"cross_attn_layers": [
|
| 25 |
+
0,
|
| 26 |
+
1,
|
| 27 |
+
2,
|
| 28 |
+
3
|
| 29 |
+
],
|
| 30 |
+
"decoder_start_token_id": null,
|
| 31 |
+
"diversity_penalty": 0.0,
|
| 32 |
+
"do_sample": false,
|
| 33 |
+
"early_stopping": false,
|
| 34 |
+
"encoder_cross_attn_layers": [
|
| 35 |
+
2
|
| 36 |
+
],
|
| 37 |
+
"encoder_hidden_size": 1280,
|
| 38 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 39 |
+
"eos_token_id": 1,
|
| 40 |
+
"exponential_decay_length_penalty": null,
|
| 41 |
+
"final_w_init_variance_scale": 0.5,
|
| 42 |
+
"finetuning_task": null,
|
| 43 |
+
"forced_bos_token_id": null,
|
| 44 |
+
"forced_eos_token_id": null,
|
| 45 |
+
"global_attn_layers": [
|
| 46 |
+
0,
|
| 47 |
+
1,
|
| 48 |
+
3
|
| 49 |
+
],
|
| 50 |
+
"head_dim": 64,
|
| 51 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 52 |
+
"hidden_size": 512,
|
| 53 |
+
"id2label": {
|
| 54 |
+
"0": "LABEL_0",
|
| 55 |
+
"1": "LABEL_1"
|
| 56 |
+
},
|
| 57 |
+
"init_std": 0.02,
|
| 58 |
+
"intermediate_size": 2048,
|
| 59 |
+
"is_decoder": false,
|
| 60 |
+
"is_encoder_decoder": false,
|
| 61 |
+
"label2id": {
|
| 62 |
+
"LABEL_0": 0,
|
| 63 |
+
"LABEL_1": 1
|
| 64 |
+
},
|
| 65 |
+
"length_penalty": 1.0,
|
| 66 |
+
"logits_soft_cap": 30.0,
|
| 67 |
+
"lru_width": 512,
|
| 68 |
+
"max_length": 20,
|
| 69 |
+
"min_length": 0,
|
| 70 |
+
"model_type": "surya_ocr",
|
| 71 |
+
"no_repeat_ngram_size": 0,
|
| 72 |
+
"num_attention_heads": 8,
|
| 73 |
+
"num_beam_groups": 1,
|
| 74 |
+
"num_beams": 1,
|
| 75 |
+
"num_hidden_layers": 4,
|
| 76 |
+
"num_key_value_heads": 2,
|
| 77 |
+
"num_return_sequences": 1,
|
| 78 |
+
"output_attentions": false,
|
| 79 |
+
"output_hidden_states": false,
|
| 80 |
+
"output_scores": false,
|
| 81 |
+
"pad_token_id": 0,
|
| 82 |
+
"prefix": null,
|
| 83 |
+
"problem_type": null,
|
| 84 |
+
"pruned_heads": {},
|
| 85 |
+
"remove_invalid_values": false,
|
| 86 |
+
"repetition_penalty": 1.0,
|
| 87 |
+
"return_dict": true,
|
| 88 |
+
"return_dict_in_generate": false,
|
| 89 |
+
"rms_norm_eps": 1e-06,
|
| 90 |
+
"rope_theta": 10000.0,
|
| 91 |
+
"self_attn_layers": [
|
| 92 |
+
1,
|
| 93 |
+
3
|
| 94 |
+
],
|
| 95 |
+
"sep_token_id": null,
|
| 96 |
+
"suppress_tokens": null,
|
| 97 |
+
"task_specific_params": null,
|
| 98 |
+
"temperature": 1.0,
|
| 99 |
+
"tf_legacy_loss": false,
|
| 100 |
+
"tie_encoder_decoder": false,
|
| 101 |
+
"tie_word_embeddings": false,
|
| 102 |
+
"tokenizer_class": null,
|
| 103 |
+
"top_k": 50,
|
| 104 |
+
"top_p": 1.0,
|
| 105 |
+
"torch_dtype": null,
|
| 106 |
+
"torchscript": false,
|
| 107 |
+
"typical_p": 1.0,
|
| 108 |
+
"use_bfloat16": false,
|
| 109 |
+
"use_cache": true,
|
| 110 |
+
"vocab_size": 65792,
|
| 111 |
+
"w_init_variance_scale": 0.01
|
| 112 |
+
},
|
| 113 |
+
"decoder_start_token_id": 1,
|
| 114 |
+
"encoder": {
|
| 115 |
+
"_name_or_path": "",
|
| 116 |
+
"add_cross_attention": false,
|
| 117 |
+
"architectures": null,
|
| 118 |
+
"attention_probs_dropout_prob": 0.0,
|
| 119 |
+
"bad_words_ids": null,
|
| 120 |
+
"begin_suppress_tokens": null,
|
| 121 |
+
"bos_token_id": null,
|
| 122 |
+
"chunk_size_feed_forward": 0,
|
| 123 |
+
"cross_attention_hidden_size": null,
|
| 124 |
+
"decoder_start_token_id": null,
|
| 125 |
+
"depths": [
|
| 126 |
+
2,
|
| 127 |
+
2,
|
| 128 |
+
18,
|
| 129 |
+
2
|
| 130 |
+
],
|
| 131 |
+
"diversity_penalty": 0.0,
|
| 132 |
+
"do_sample": false,
|
| 133 |
+
"drop_path_rate": 0.1,
|
| 134 |
+
"early_stopping": false,
|
| 135 |
+
"embed_dim": 128,
|
| 136 |
+
"encoder_length": 256,
|
| 137 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 138 |
+
"eos_token_id": null,
|
| 139 |
+
"exponential_decay_length_penalty": null,
|
| 140 |
+
"finetuning_task": null,
|
| 141 |
+
"forced_bos_token_id": null,
|
| 142 |
+
"forced_eos_token_id": null,
|
| 143 |
+
"hidden_act": "gelu",
|
| 144 |
+
"hidden_dropout_prob": 0.0,
|
| 145 |
+
"hidden_size": 1024,
|
| 146 |
+
"id2label": {
|
| 147 |
+
"0": "LABEL_0",
|
| 148 |
+
"1": "LABEL_1"
|
| 149 |
+
},
|
| 150 |
+
"image_size": [
|
| 151 |
+
256,
|
| 152 |
+
896
|
| 153 |
+
],
|
| 154 |
+
"initializer_range": 0.02,
|
| 155 |
+
"is_decoder": false,
|
| 156 |
+
"is_encoder_decoder": false,
|
| 157 |
+
"label2id": {
|
| 158 |
+
"LABEL_0": 0,
|
| 159 |
+
"LABEL_1": 1
|
| 160 |
+
},
|
| 161 |
+
"layer_norm_eps": 1e-05,
|
| 162 |
+
"length_penalty": 1.0,
|
| 163 |
+
"max_length": 20,
|
| 164 |
+
"min_length": 0,
|
| 165 |
+
"mlp_ratio": 4.0,
|
| 166 |
+
"model_type": "donut-swin",
|
| 167 |
+
"no_repeat_ngram_size": 0,
|
| 168 |
+
"num_beam_groups": 1,
|
| 169 |
+
"num_beams": 1,
|
| 170 |
+
"num_channels": 3,
|
| 171 |
+
"num_heads": [
|
| 172 |
+
4,
|
| 173 |
+
8,
|
| 174 |
+
16,
|
| 175 |
+
32
|
| 176 |
+
],
|
| 177 |
+
"num_kv_heads": [
|
| 178 |
+
4,
|
| 179 |
+
8,
|
| 180 |
+
16,
|
| 181 |
+
32
|
| 182 |
+
],
|
| 183 |
+
"num_layers": 4,
|
| 184 |
+
"num_return_sequences": 1,
|
| 185 |
+
"output_attentions": false,
|
| 186 |
+
"output_hidden_states": false,
|
| 187 |
+
"output_scores": false,
|
| 188 |
+
"pad_token_id": null,
|
| 189 |
+
"patch_size": 4,
|
| 190 |
+
"prefix": null,
|
| 191 |
+
"problem_type": null,
|
| 192 |
+
"pruned_heads": {},
|
| 193 |
+
"qkv_bias": true,
|
| 194 |
+
"remove_invalid_values": false,
|
| 195 |
+
"repetition_penalty": 1.0,
|
| 196 |
+
"return_dict": true,
|
| 197 |
+
"return_dict_in_generate": false,
|
| 198 |
+
"sep_token_id": null,
|
| 199 |
+
"suppress_tokens": null,
|
| 200 |
+
"task_specific_params": null,
|
| 201 |
+
"temperature": 1.0,
|
| 202 |
+
"tf_legacy_loss": false,
|
| 203 |
+
"tie_encoder_decoder": false,
|
| 204 |
+
"tie_word_embeddings": true,
|
| 205 |
+
"tokenizer_class": null,
|
| 206 |
+
"top_k": 50,
|
| 207 |
+
"top_p": 1.0,
|
| 208 |
+
"torch_dtype": null,
|
| 209 |
+
"torchscript": false,
|
| 210 |
+
"typical_p": 1.0,
|
| 211 |
+
"use_absolute_embeddings": true,
|
| 212 |
+
"use_bfloat16": false,
|
| 213 |
+
"window_size": 8
|
| 214 |
+
},
|
| 215 |
+
"eos_token_id": 1,
|
| 216 |
+
"is_encoder_decoder": true,
|
| 217 |
+
"model_type": "vision-encoder-decoder",
|
| 218 |
+
"pad_token_id": 0,
|
| 219 |
+
"text_encoder": {
|
| 220 |
+
"_name_or_path": "",
|
| 221 |
+
"add_cross_attention": false,
|
| 222 |
+
"architectures": null,
|
| 223 |
+
"attention_bias": false,
|
| 224 |
+
"attention_dropout": 0.0,
|
| 225 |
+
"attention_window_size": 16,
|
| 226 |
+
"aux_heads": 0,
|
| 227 |
+
"bad_words_ids": null,
|
| 228 |
+
"begin_suppress_tokens": null,
|
| 229 |
+
"block_types": [
|
| 230 |
+
"attention"
|
| 231 |
+
],
|
| 232 |
+
"bos_token_id": 1,
|
| 233 |
+
"causal": false,
|
| 234 |
+
"chunk_size_feed_forward": 0,
|
| 235 |
+
"conv1d_width": 4,
|
| 236 |
+
"cross_attention_hidden_size": null,
|
| 237 |
+
"cross_attn_layers": [
|
| 238 |
+
0,
|
| 239 |
+
1,
|
| 240 |
+
2,
|
| 241 |
+
3,
|
| 242 |
+
4,
|
| 243 |
+
6,
|
| 244 |
+
8,
|
| 245 |
+
10,
|
| 246 |
+
11
|
| 247 |
+
],
|
| 248 |
+
"decoder_start_token_id": null,
|
| 249 |
+
"diversity_penalty": 0.0,
|
| 250 |
+
"do_sample": false,
|
| 251 |
+
"early_stopping": false,
|
| 252 |
+
"encoder_hidden_size": 1024,
|
| 253 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 254 |
+
"eos_token_id": 1,
|
| 255 |
+
"exponential_decay_length_penalty": null,
|
| 256 |
+
"final_w_init_variance_scale": 0.16666666666666666,
|
| 257 |
+
"finetuning_task": null,
|
| 258 |
+
"forced_bos_token_id": null,
|
| 259 |
+
"forced_eos_token_id": null,
|
| 260 |
+
"global_attn_layers": [
|
| 261 |
+
0,
|
| 262 |
+
1,
|
| 263 |
+
3,
|
| 264 |
+
5,
|
| 265 |
+
7,
|
| 266 |
+
9,
|
| 267 |
+
11
|
| 268 |
+
],
|
| 269 |
+
"head_dim": 80,
|
| 270 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 271 |
+
"hidden_size": 1280,
|
| 272 |
+
"id2label": {
|
| 273 |
+
"0": "LABEL_0",
|
| 274 |
+
"1": "LABEL_1"
|
| 275 |
+
},
|
| 276 |
+
"init_std": 0.02,
|
| 277 |
+
"intermediate_size": 5120,
|
| 278 |
+
"is_decoder": false,
|
| 279 |
+
"is_encoder_decoder": false,
|
| 280 |
+
"iteration_count": 1,
|
| 281 |
+
"label2id": {
|
| 282 |
+
"LABEL_0": 0,
|
| 283 |
+
"LABEL_1": 1
|
| 284 |
+
},
|
| 285 |
+
"length_penalty": 1.0,
|
| 286 |
+
"logits_soft_cap": 30.0,
|
| 287 |
+
"lru_width": 1280,
|
| 288 |
+
"max_length": 20,
|
| 289 |
+
"min_length": 0,
|
| 290 |
+
"model_type": "surya_ocr",
|
| 291 |
+
"no_repeat_ngram_size": 0,
|
| 292 |
+
"num_attention_heads": 16,
|
| 293 |
+
"num_beam_groups": 1,
|
| 294 |
+
"num_beams": 1,
|
| 295 |
+
"num_hidden_layers": 12,
|
| 296 |
+
"num_key_value_heads": 4,
|
| 297 |
+
"num_return_sequences": 1,
|
| 298 |
+
"output_attentions": false,
|
| 299 |
+
"output_hidden_states": false,
|
| 300 |
+
"output_scores": false,
|
| 301 |
+
"pad_token_id": 0,
|
| 302 |
+
"prefix": null,
|
| 303 |
+
"problem_type": null,
|
| 304 |
+
"pruned_heads": {},
|
| 305 |
+
"query_token_count": 128,
|
| 306 |
+
"remove_invalid_values": false,
|
| 307 |
+
"repetition_penalty": 1.0,
|
| 308 |
+
"return_dict": true,
|
| 309 |
+
"return_dict_in_generate": false,
|
| 310 |
+
"rms_norm_eps": 1e-06,
|
| 311 |
+
"rope_theta": 10000.0,
|
| 312 |
+
"self_attn_layers": [
|
| 313 |
+
1,
|
| 314 |
+
3,
|
| 315 |
+
5,
|
| 316 |
+
7,
|
| 317 |
+
9,
|
| 318 |
+
11
|
| 319 |
+
],
|
| 320 |
+
"sep_token_id": null,
|
| 321 |
+
"suppress_tokens": null,
|
| 322 |
+
"task_specific_params": null,
|
| 323 |
+
"temperature": 1.0,
|
| 324 |
+
"tf_legacy_loss": false,
|
| 325 |
+
"tie_encoder_decoder": false,
|
| 326 |
+
"tie_word_embeddings": true,
|
| 327 |
+
"tokenizer_class": null,
|
| 328 |
+
"top_k": 50,
|
| 329 |
+
"top_p": 1.0,
|
| 330 |
+
"torch_dtype": null,
|
| 331 |
+
"torchscript": false,
|
| 332 |
+
"typical_p": 1.0,
|
| 333 |
+
"use_bfloat16": false,
|
| 334 |
+
"use_cache": true,
|
| 335 |
+
"vocab_size": 256,
|
| 336 |
+
"w_init_variance_scale": 0.01
|
| 337 |
+
},
|
| 338 |
+
"tie_word_embeddings": false,
|
| 339 |
+
"torch_dtype": "float32",
|
| 340 |
+
"transformers_version": "4.44.2"
|
| 341 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"decoder_start_token_id": 1,
|
| 5 |
+
"eos_token_id": 1,
|
| 6 |
+
"pad_token_id": 0,
|
| 7 |
+
"transformers_version": "4.44.2"
|
| 8 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:697d2b26acc2e977b689f0fd519b698eb607a8b081218e88982e92b60d284825
|
| 3 |
+
size 1880195368
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_align_long_axis": true,
|
| 3 |
+
"do_normalize": false,
|
| 4 |
+
"do_pad": false,
|
| 5 |
+
"do_rescale": false,
|
| 6 |
+
"do_resize": false,
|
| 7 |
+
"do_thumbnail": false,
|
| 8 |
+
"image_mean": [
|
| 9 |
+
0.5,
|
| 10 |
+
0.5,
|
| 11 |
+
0.5
|
| 12 |
+
],
|
| 13 |
+
"image_processor_type": "SuryaImageProcessor",
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"max_size": {
|
| 20 |
+
"height": 256,
|
| 21 |
+
"width": 896
|
| 22 |
+
},
|
| 23 |
+
"patch_size": [
|
| 24 |
+
4,
|
| 25 |
+
4
|
| 26 |
+
],
|
| 27 |
+
"processor_class": "SuryaProcessor",
|
| 28 |
+
"resample": 2,
|
| 29 |
+
"rescale_factor": 0.00392156862745098,
|
| 30 |
+
"size": {
|
| 31 |
+
"height": 2560,
|
| 32 |
+
"width": 1920
|
| 33 |
+
},
|
| 34 |
+
"train": false
|
| 35 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,150 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>",
|
| 103 |
+
"<extra_id_100>",
|
| 104 |
+
"<extra_id_101>",
|
| 105 |
+
"<extra_id_102>",
|
| 106 |
+
"<extra_id_103>",
|
| 107 |
+
"<extra_id_104>",
|
| 108 |
+
"<extra_id_105>",
|
| 109 |
+
"<extra_id_106>",
|
| 110 |
+
"<extra_id_107>",
|
| 111 |
+
"<extra_id_108>",
|
| 112 |
+
"<extra_id_109>",
|
| 113 |
+
"<extra_id_110>",
|
| 114 |
+
"<extra_id_111>",
|
| 115 |
+
"<extra_id_112>",
|
| 116 |
+
"<extra_id_113>",
|
| 117 |
+
"<extra_id_114>",
|
| 118 |
+
"<extra_id_115>",
|
| 119 |
+
"<extra_id_116>",
|
| 120 |
+
"<extra_id_117>",
|
| 121 |
+
"<extra_id_118>",
|
| 122 |
+
"<extra_id_119>",
|
| 123 |
+
"<extra_id_120>",
|
| 124 |
+
"<extra_id_121>",
|
| 125 |
+
"<extra_id_122>",
|
| 126 |
+
"<extra_id_123>",
|
| 127 |
+
"<extra_id_124>"
|
| 128 |
+
],
|
| 129 |
+
"eos_token": {
|
| 130 |
+
"content": "</s>",
|
| 131 |
+
"lstrip": true,
|
| 132 |
+
"normalized": true,
|
| 133 |
+
"rstrip": true,
|
| 134 |
+
"single_word": false
|
| 135 |
+
},
|
| 136 |
+
"pad_token": {
|
| 137 |
+
"content": "<pad>",
|
| 138 |
+
"lstrip": true,
|
| 139 |
+
"normalized": true,
|
| 140 |
+
"rstrip": true,
|
| 141 |
+
"single_word": false
|
| 142 |
+
},
|
| 143 |
+
"unk_token": {
|
| 144 |
+
"content": "<unk>",
|
| 145 |
+
"lstrip": true,
|
| 146 |
+
"normalized": true,
|
| 147 |
+
"rstrip": true,
|
| 148 |
+
"single_word": false
|
| 149 |
+
}
|
| 150 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,1163 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": true,
|
| 6 |
+
"normalized": true,
|
| 7 |
+
"rstrip": true,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "</s>",
|
| 13 |
+
"lstrip": true,
|
| 14 |
+
"normalized": true,
|
| 15 |
+
"rstrip": true,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<unk>",
|
| 21 |
+
"lstrip": true,
|
| 22 |
+
"normalized": true,
|
| 23 |
+
"rstrip": true,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"259": {
|
| 28 |
+
"content": "<extra_id_0>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"260": {
|
| 36 |
+
"content": "<extra_id_1>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"261": {
|
| 44 |
+
"content": "<extra_id_2>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"262": {
|
| 52 |
+
"content": "<extra_id_3>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"263": {
|
| 60 |
+
"content": "<extra_id_4>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"264": {
|
| 68 |
+
"content": "<extra_id_5>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"265": {
|
| 76 |
+
"content": "<extra_id_6>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"266": {
|
| 84 |
+
"content": "<extra_id_7>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"267": {
|
| 92 |
+
"content": "<extra_id_8>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"268": {
|
| 100 |
+
"content": "<extra_id_9>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"269": {
|
| 108 |
+
"content": "<extra_id_10>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"270": {
|
| 116 |
+
"content": "<extra_id_11>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"271": {
|
| 124 |
+
"content": "<extra_id_12>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"272": {
|
| 132 |
+
"content": "<extra_id_13>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"273": {
|
| 140 |
+
"content": "<extra_id_14>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"274": {
|
| 148 |
+
"content": "<extra_id_15>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"275": {
|
| 156 |
+
"content": "<extra_id_16>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"276": {
|
| 164 |
+
"content": "<extra_id_17>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"277": {
|
| 172 |
+
"content": "<extra_id_18>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"278": {
|
| 180 |
+
"content": "<extra_id_19>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"279": {
|
| 188 |
+
"content": "<extra_id_20>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"280": {
|
| 196 |
+
"content": "<extra_id_21>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"281": {
|
| 204 |
+
"content": "<extra_id_22>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"282": {
|
| 212 |
+
"content": "<extra_id_23>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"283": {
|
| 220 |
+
"content": "<extra_id_24>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"284": {
|
| 228 |
+
"content": "<extra_id_25>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"285": {
|
| 236 |
+
"content": "<extra_id_26>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"286": {
|
| 244 |
+
"content": "<extra_id_27>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"287": {
|
| 252 |
+
"content": "<extra_id_28>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"288": {
|
| 260 |
+
"content": "<extra_id_29>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"289": {
|
| 268 |
+
"content": "<extra_id_30>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"290": {
|
| 276 |
+
"content": "<extra_id_31>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"291": {
|
| 284 |
+
"content": "<extra_id_32>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"292": {
|
| 292 |
+
"content": "<extra_id_33>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"293": {
|
| 300 |
+
"content": "<extra_id_34>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"294": {
|
| 308 |
+
"content": "<extra_id_35>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"295": {
|
| 316 |
+
"content": "<extra_id_36>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"296": {
|
| 324 |
+
"content": "<extra_id_37>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"297": {
|
| 332 |
+
"content": "<extra_id_38>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"298": {
|
| 340 |
+
"content": "<extra_id_39>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"299": {
|
| 348 |
+
"content": "<extra_id_40>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"300": {
|
| 356 |
+
"content": "<extra_id_41>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"301": {
|
| 364 |
+
"content": "<extra_id_42>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"302": {
|
| 372 |
+
"content": "<extra_id_43>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"303": {
|
| 380 |
+
"content": "<extra_id_44>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"304": {
|
| 388 |
+
"content": "<extra_id_45>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"305": {
|
| 396 |
+
"content": "<extra_id_46>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"306": {
|
| 404 |
+
"content": "<extra_id_47>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"307": {
|
| 412 |
+
"content": "<extra_id_48>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"308": {
|
| 420 |
+
"content": "<extra_id_49>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"309": {
|
| 428 |
+
"content": "<extra_id_50>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"310": {
|
| 436 |
+
"content": "<extra_id_51>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"311": {
|
| 444 |
+
"content": "<extra_id_52>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"312": {
|
| 452 |
+
"content": "<extra_id_53>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"313": {
|
| 460 |
+
"content": "<extra_id_54>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"314": {
|
| 468 |
+
"content": "<extra_id_55>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"315": {
|
| 476 |
+
"content": "<extra_id_56>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"316": {
|
| 484 |
+
"content": "<extra_id_57>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"317": {
|
| 492 |
+
"content": "<extra_id_58>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"318": {
|
| 500 |
+
"content": "<extra_id_59>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"319": {
|
| 508 |
+
"content": "<extra_id_60>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"320": {
|
| 516 |
+
"content": "<extra_id_61>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"321": {
|
| 524 |
+
"content": "<extra_id_62>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"322": {
|
| 532 |
+
"content": "<extra_id_63>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"323": {
|
| 540 |
+
"content": "<extra_id_64>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"324": {
|
| 548 |
+
"content": "<extra_id_65>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"325": {
|
| 556 |
+
"content": "<extra_id_66>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"326": {
|
| 564 |
+
"content": "<extra_id_67>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"327": {
|
| 572 |
+
"content": "<extra_id_68>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"328": {
|
| 580 |
+
"content": "<extra_id_69>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"329": {
|
| 588 |
+
"content": "<extra_id_70>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"330": {
|
| 596 |
+
"content": "<extra_id_71>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"331": {
|
| 604 |
+
"content": "<extra_id_72>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"332": {
|
| 612 |
+
"content": "<extra_id_73>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"333": {
|
| 620 |
+
"content": "<extra_id_74>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"334": {
|
| 628 |
+
"content": "<extra_id_75>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"335": {
|
| 636 |
+
"content": "<extra_id_76>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"336": {
|
| 644 |
+
"content": "<extra_id_77>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"337": {
|
| 652 |
+
"content": "<extra_id_78>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"338": {
|
| 660 |
+
"content": "<extra_id_79>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"339": {
|
| 668 |
+
"content": "<extra_id_80>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"340": {
|
| 676 |
+
"content": "<extra_id_81>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"341": {
|
| 684 |
+
"content": "<extra_id_82>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"342": {
|
| 692 |
+
"content": "<extra_id_83>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"343": {
|
| 700 |
+
"content": "<extra_id_84>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"344": {
|
| 708 |
+
"content": "<extra_id_85>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"345": {
|
| 716 |
+
"content": "<extra_id_86>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"346": {
|
| 724 |
+
"content": "<extra_id_87>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"347": {
|
| 732 |
+
"content": "<extra_id_88>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"348": {
|
| 740 |
+
"content": "<extra_id_89>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"349": {
|
| 748 |
+
"content": "<extra_id_90>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"350": {
|
| 756 |
+
"content": "<extra_id_91>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"351": {
|
| 764 |
+
"content": "<extra_id_92>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"352": {
|
| 772 |
+
"content": "<extra_id_93>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"353": {
|
| 780 |
+
"content": "<extra_id_94>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"354": {
|
| 788 |
+
"content": "<extra_id_95>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"355": {
|
| 796 |
+
"content": "<extra_id_96>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"356": {
|
| 804 |
+
"content": "<extra_id_97>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"357": {
|
| 812 |
+
"content": "<extra_id_98>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"358": {
|
| 820 |
+
"content": "<extra_id_99>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"359": {
|
| 828 |
+
"content": "<extra_id_100>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"360": {
|
| 836 |
+
"content": "<extra_id_101>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"361": {
|
| 844 |
+
"content": "<extra_id_102>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"362": {
|
| 852 |
+
"content": "<extra_id_103>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"363": {
|
| 860 |
+
"content": "<extra_id_104>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"364": {
|
| 868 |
+
"content": "<extra_id_105>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"365": {
|
| 876 |
+
"content": "<extra_id_106>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"366": {
|
| 884 |
+
"content": "<extra_id_107>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"367": {
|
| 892 |
+
"content": "<extra_id_108>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"368": {
|
| 900 |
+
"content": "<extra_id_109>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"369": {
|
| 908 |
+
"content": "<extra_id_110>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"370": {
|
| 916 |
+
"content": "<extra_id_111>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"371": {
|
| 924 |
+
"content": "<extra_id_112>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"372": {
|
| 932 |
+
"content": "<extra_id_113>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"373": {
|
| 940 |
+
"content": "<extra_id_114>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"374": {
|
| 948 |
+
"content": "<extra_id_115>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"375": {
|
| 956 |
+
"content": "<extra_id_116>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"376": {
|
| 964 |
+
"content": "<extra_id_117>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"377": {
|
| 972 |
+
"content": "<extra_id_118>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"378": {
|
| 980 |
+
"content": "<extra_id_119>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"379": {
|
| 988 |
+
"content": "<extra_id_120>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"380": {
|
| 996 |
+
"content": "<extra_id_121>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"381": {
|
| 1004 |
+
"content": "<extra_id_122>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"382": {
|
| 1012 |
+
"content": "<extra_id_123>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"383": {
|
| 1020 |
+
"content": "<extra_id_124>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
}
|
| 1027 |
+
},
|
| 1028 |
+
"additional_special_tokens": [
|
| 1029 |
+
"<extra_id_0>",
|
| 1030 |
+
"<extra_id_1>",
|
| 1031 |
+
"<extra_id_2>",
|
| 1032 |
+
"<extra_id_3>",
|
| 1033 |
+
"<extra_id_4>",
|
| 1034 |
+
"<extra_id_5>",
|
| 1035 |
+
"<extra_id_6>",
|
| 1036 |
+
"<extra_id_7>",
|
| 1037 |
+
"<extra_id_8>",
|
| 1038 |
+
"<extra_id_9>",
|
| 1039 |
+
"<extra_id_10>",
|
| 1040 |
+
"<extra_id_11>",
|
| 1041 |
+
"<extra_id_12>",
|
| 1042 |
+
"<extra_id_13>",
|
| 1043 |
+
"<extra_id_14>",
|
| 1044 |
+
"<extra_id_15>",
|
| 1045 |
+
"<extra_id_16>",
|
| 1046 |
+
"<extra_id_17>",
|
| 1047 |
+
"<extra_id_18>",
|
| 1048 |
+
"<extra_id_19>",
|
| 1049 |
+
"<extra_id_20>",
|
| 1050 |
+
"<extra_id_21>",
|
| 1051 |
+
"<extra_id_22>",
|
| 1052 |
+
"<extra_id_23>",
|
| 1053 |
+
"<extra_id_24>",
|
| 1054 |
+
"<extra_id_25>",
|
| 1055 |
+
"<extra_id_26>",
|
| 1056 |
+
"<extra_id_27>",
|
| 1057 |
+
"<extra_id_28>",
|
| 1058 |
+
"<extra_id_29>",
|
| 1059 |
+
"<extra_id_30>",
|
| 1060 |
+
"<extra_id_31>",
|
| 1061 |
+
"<extra_id_32>",
|
| 1062 |
+
"<extra_id_33>",
|
| 1063 |
+
"<extra_id_34>",
|
| 1064 |
+
"<extra_id_35>",
|
| 1065 |
+
"<extra_id_36>",
|
| 1066 |
+
"<extra_id_37>",
|
| 1067 |
+
"<extra_id_38>",
|
| 1068 |
+
"<extra_id_39>",
|
| 1069 |
+
"<extra_id_40>",
|
| 1070 |
+
"<extra_id_41>",
|
| 1071 |
+
"<extra_id_42>",
|
| 1072 |
+
"<extra_id_43>",
|
| 1073 |
+
"<extra_id_44>",
|
| 1074 |
+
"<extra_id_45>",
|
| 1075 |
+
"<extra_id_46>",
|
| 1076 |
+
"<extra_id_47>",
|
| 1077 |
+
"<extra_id_48>",
|
| 1078 |
+
"<extra_id_49>",
|
| 1079 |
+
"<extra_id_50>",
|
| 1080 |
+
"<extra_id_51>",
|
| 1081 |
+
"<extra_id_52>",
|
| 1082 |
+
"<extra_id_53>",
|
| 1083 |
+
"<extra_id_54>",
|
| 1084 |
+
"<extra_id_55>",
|
| 1085 |
+
"<extra_id_56>",
|
| 1086 |
+
"<extra_id_57>",
|
| 1087 |
+
"<extra_id_58>",
|
| 1088 |
+
"<extra_id_59>",
|
| 1089 |
+
"<extra_id_60>",
|
| 1090 |
+
"<extra_id_61>",
|
| 1091 |
+
"<extra_id_62>",
|
| 1092 |
+
"<extra_id_63>",
|
| 1093 |
+
"<extra_id_64>",
|
| 1094 |
+
"<extra_id_65>",
|
| 1095 |
+
"<extra_id_66>",
|
| 1096 |
+
"<extra_id_67>",
|
| 1097 |
+
"<extra_id_68>",
|
| 1098 |
+
"<extra_id_69>",
|
| 1099 |
+
"<extra_id_70>",
|
| 1100 |
+
"<extra_id_71>",
|
| 1101 |
+
"<extra_id_72>",
|
| 1102 |
+
"<extra_id_73>",
|
| 1103 |
+
"<extra_id_74>",
|
| 1104 |
+
"<extra_id_75>",
|
| 1105 |
+
"<extra_id_76>",
|
| 1106 |
+
"<extra_id_77>",
|
| 1107 |
+
"<extra_id_78>",
|
| 1108 |
+
"<extra_id_79>",
|
| 1109 |
+
"<extra_id_80>",
|
| 1110 |
+
"<extra_id_81>",
|
| 1111 |
+
"<extra_id_82>",
|
| 1112 |
+
"<extra_id_83>",
|
| 1113 |
+
"<extra_id_84>",
|
| 1114 |
+
"<extra_id_85>",
|
| 1115 |
+
"<extra_id_86>",
|
| 1116 |
+
"<extra_id_87>",
|
| 1117 |
+
"<extra_id_88>",
|
| 1118 |
+
"<extra_id_89>",
|
| 1119 |
+
"<extra_id_90>",
|
| 1120 |
+
"<extra_id_91>",
|
| 1121 |
+
"<extra_id_92>",
|
| 1122 |
+
"<extra_id_93>",
|
| 1123 |
+
"<extra_id_94>",
|
| 1124 |
+
"<extra_id_95>",
|
| 1125 |
+
"<extra_id_96>",
|
| 1126 |
+
"<extra_id_97>",
|
| 1127 |
+
"<extra_id_98>",
|
| 1128 |
+
"<extra_id_99>",
|
| 1129 |
+
"<extra_id_100>",
|
| 1130 |
+
"<extra_id_101>",
|
| 1131 |
+
"<extra_id_102>",
|
| 1132 |
+
"<extra_id_103>",
|
| 1133 |
+
"<extra_id_104>",
|
| 1134 |
+
"<extra_id_105>",
|
| 1135 |
+
"<extra_id_106>",
|
| 1136 |
+
"<extra_id_107>",
|
| 1137 |
+
"<extra_id_108>",
|
| 1138 |
+
"<extra_id_109>",
|
| 1139 |
+
"<extra_id_110>",
|
| 1140 |
+
"<extra_id_111>",
|
| 1141 |
+
"<extra_id_112>",
|
| 1142 |
+
"<extra_id_113>",
|
| 1143 |
+
"<extra_id_114>",
|
| 1144 |
+
"<extra_id_115>",
|
| 1145 |
+
"<extra_id_116>",
|
| 1146 |
+
"<extra_id_117>",
|
| 1147 |
+
"<extra_id_118>",
|
| 1148 |
+
"<extra_id_119>",
|
| 1149 |
+
"<extra_id_120>",
|
| 1150 |
+
"<extra_id_121>",
|
| 1151 |
+
"<extra_id_122>",
|
| 1152 |
+
"<extra_id_123>",
|
| 1153 |
+
"<extra_id_124>"
|
| 1154 |
+
],
|
| 1155 |
+
"clean_up_tokenization_spaces": true,
|
| 1156 |
+
"eos_token": "</s>",
|
| 1157 |
+
"extra_ids": 0,
|
| 1158 |
+
"model_max_length": 175,
|
| 1159 |
+
"pad_token": "<pad>",
|
| 1160 |
+
"processor_class": "SuryaProcessor",
|
| 1161 |
+
"tokenizer_class": "Byt5LangTokenizer",
|
| 1162 |
+
"unk_token": "<unk>"
|
| 1163 |
+
}
|