Upload folder using huggingface_hub
Browse files- added_tokens.json +86 -0
- config.json +192 -0
- generation_config.json +10 -0
- model.safetensors +3 -0
- preprocessor_config.json +26 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +101 -0
- tokenizer.json +0 -0
- tokenizer_config.json +749 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</s_None>": 57564,
|
| 3 |
+
"</s_client>": 57534,
|
| 4 |
+
"</s_client_tax_id>": 57538,
|
| 5 |
+
"</s_date>": 57572,
|
| 6 |
+
"</s_document_number>": 57600,
|
| 7 |
+
"</s_document_series>": 57604,
|
| 8 |
+
"</s_document_type>": 57601,
|
| 9 |
+
"</s_header>": 57526,
|
| 10 |
+
"</s_iban>": 57540,
|
| 11 |
+
"</s_ignore>": 57582,
|
| 12 |
+
"</s_invoice_date>": 57530,
|
| 13 |
+
"</s_invoice_no>": 57528,
|
| 14 |
+
"</s_issue_date>": 57602,
|
| 15 |
+
"</s_issuer_ruc>": 57599,
|
| 16 |
+
"</s_item_desc>": 57544,
|
| 17 |
+
"</s_item_gross_worth>": 57554,
|
| 18 |
+
"</s_item_key>": 57588,
|
| 19 |
+
"</s_item_name>": 57590,
|
| 20 |
+
"</s_item_net_price>": 57548,
|
| 21 |
+
"</s_item_net_worth>": 57550,
|
| 22 |
+
"</s_item_qty>": 57546,
|
| 23 |
+
"</s_item_quantity>": 57594,
|
| 24 |
+
"</s_item_value>": 57592,
|
| 25 |
+
"</s_item_vat>": 57552,
|
| 26 |
+
"</s_items>": 57542,
|
| 27 |
+
"</s_line_items>": 57586,
|
| 28 |
+
"</s_seller>": 57532,
|
| 29 |
+
"</s_seller_tax_id>": 57536,
|
| 30 |
+
"</s_store_addr>": 57568,
|
| 31 |
+
"</s_store_name>": 57566,
|
| 32 |
+
"</s_subtotal>": 57576,
|
| 33 |
+
"</s_summary>": 57556,
|
| 34 |
+
"</s_tax>": 57578,
|
| 35 |
+
"</s_telephone>": 57570,
|
| 36 |
+
"</s_time>": 57574,
|
| 37 |
+
"</s_tips>": 57584,
|
| 38 |
+
"</s_total>": 57580,
|
| 39 |
+
"</s_total_gross_worth>": 57562,
|
| 40 |
+
"</s_total_net_worth>": 57558,
|
| 41 |
+
"</s_total_vat>": 57560,
|
| 42 |
+
"<s_None>": 57563,
|
| 43 |
+
"<s_client>": 57533,
|
| 44 |
+
"<s_client_tax_id>": 57537,
|
| 45 |
+
"<s_date>": 57571,
|
| 46 |
+
"<s_document_number>": 57605,
|
| 47 |
+
"<s_document_series>": 57596,
|
| 48 |
+
"<s_document_type>": 57603,
|
| 49 |
+
"<s_header>": 57525,
|
| 50 |
+
"<s_iban>": 57539,
|
| 51 |
+
"<s_ignore>": 57581,
|
| 52 |
+
"<s_iitcdip>": 57523,
|
| 53 |
+
"<s_invoice_date>": 57529,
|
| 54 |
+
"<s_invoice_no>": 57527,
|
| 55 |
+
"<s_issue_date>": 57597,
|
| 56 |
+
"<s_issuer_ruc>": 57598,
|
| 57 |
+
"<s_item_desc>": 57543,
|
| 58 |
+
"<s_item_gross_worth>": 57553,
|
| 59 |
+
"<s_item_key>": 57587,
|
| 60 |
+
"<s_item_name>": 57589,
|
| 61 |
+
"<s_item_net_price>": 57547,
|
| 62 |
+
"<s_item_net_worth>": 57549,
|
| 63 |
+
"<s_item_qty>": 57545,
|
| 64 |
+
"<s_item_quantity>": 57593,
|
| 65 |
+
"<s_item_value>": 57591,
|
| 66 |
+
"<s_item_vat>": 57551,
|
| 67 |
+
"<s_items>": 57541,
|
| 68 |
+
"<s_line_items>": 57585,
|
| 69 |
+
"<s_receipt>": 57595,
|
| 70 |
+
"<s_seller>": 57531,
|
| 71 |
+
"<s_seller_tax_id>": 57535,
|
| 72 |
+
"<s_store_addr>": 57567,
|
| 73 |
+
"<s_store_name>": 57565,
|
| 74 |
+
"<s_subtotal>": 57575,
|
| 75 |
+
"<s_summary>": 57555,
|
| 76 |
+
"<s_synthdog>": 57524,
|
| 77 |
+
"<s_tax>": 57577,
|
| 78 |
+
"<s_telephone>": 57569,
|
| 79 |
+
"<s_time>": 57573,
|
| 80 |
+
"<s_tips>": 57583,
|
| 81 |
+
"<s_total>": 57579,
|
| 82 |
+
"<s_total_gross_worth>": 57561,
|
| 83 |
+
"<s_total_net_worth>": 57557,
|
| 84 |
+
"<s_total_vat>": 57559,
|
| 85 |
+
"<sep/>": 57522
|
| 86 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,192 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "mychen76/invoice-and-receipts_donut_v1",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"VisionEncoderDecoderModel"
|
| 5 |
+
],
|
| 6 |
+
"decoder": {
|
| 7 |
+
"_name_or_path": "",
|
| 8 |
+
"activation_dropout": 0.0,
|
| 9 |
+
"activation_function": "gelu",
|
| 10 |
+
"add_cross_attention": true,
|
| 11 |
+
"add_final_layer_norm": true,
|
| 12 |
+
"architectures": null,
|
| 13 |
+
"attention_dropout": 0.0,
|
| 14 |
+
"bad_words_ids": null,
|
| 15 |
+
"begin_suppress_tokens": null,
|
| 16 |
+
"bos_token_id": 0,
|
| 17 |
+
"chunk_size_feed_forward": 0,
|
| 18 |
+
"classifier_dropout": 0.0,
|
| 19 |
+
"cross_attention_hidden_size": null,
|
| 20 |
+
"d_model": 1024,
|
| 21 |
+
"decoder_attention_heads": 16,
|
| 22 |
+
"decoder_ffn_dim": 4096,
|
| 23 |
+
"decoder_layerdrop": 0.0,
|
| 24 |
+
"decoder_layers": 4,
|
| 25 |
+
"decoder_start_token_id": null,
|
| 26 |
+
"diversity_penalty": 0.0,
|
| 27 |
+
"do_sample": false,
|
| 28 |
+
"dropout": 0.1,
|
| 29 |
+
"early_stopping": false,
|
| 30 |
+
"encoder_attention_heads": 16,
|
| 31 |
+
"encoder_ffn_dim": 4096,
|
| 32 |
+
"encoder_layerdrop": 0.0,
|
| 33 |
+
"encoder_layers": 12,
|
| 34 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 35 |
+
"eos_token_id": 2,
|
| 36 |
+
"exponential_decay_length_penalty": null,
|
| 37 |
+
"finetuning_task": null,
|
| 38 |
+
"forced_bos_token_id": null,
|
| 39 |
+
"forced_eos_token_id": 2,
|
| 40 |
+
"id2label": {
|
| 41 |
+
"0": "LABEL_0",
|
| 42 |
+
"1": "LABEL_1"
|
| 43 |
+
},
|
| 44 |
+
"init_std": 0.02,
|
| 45 |
+
"is_decoder": true,
|
| 46 |
+
"is_encoder_decoder": false,
|
| 47 |
+
"label2id": {
|
| 48 |
+
"LABEL_0": 0,
|
| 49 |
+
"LABEL_1": 1
|
| 50 |
+
},
|
| 51 |
+
"length_penalty": 1.0,
|
| 52 |
+
"max_length": 768,
|
| 53 |
+
"max_position_embeddings": 1536,
|
| 54 |
+
"min_length": 0,
|
| 55 |
+
"model_type": "mbart",
|
| 56 |
+
"no_repeat_ngram_size": 0,
|
| 57 |
+
"num_beam_groups": 1,
|
| 58 |
+
"num_beams": 1,
|
| 59 |
+
"num_hidden_layers": 12,
|
| 60 |
+
"num_return_sequences": 1,
|
| 61 |
+
"output_attentions": false,
|
| 62 |
+
"output_hidden_states": false,
|
| 63 |
+
"output_scores": false,
|
| 64 |
+
"pad_token_id": 1,
|
| 65 |
+
"prefix": null,
|
| 66 |
+
"problem_type": null,
|
| 67 |
+
"pruned_heads": {},
|
| 68 |
+
"remove_invalid_values": false,
|
| 69 |
+
"repetition_penalty": 1.0,
|
| 70 |
+
"return_dict": true,
|
| 71 |
+
"return_dict_in_generate": false,
|
| 72 |
+
"scale_embedding": true,
|
| 73 |
+
"sep_token_id": null,
|
| 74 |
+
"suppress_tokens": null,
|
| 75 |
+
"task_specific_params": null,
|
| 76 |
+
"temperature": 1.0,
|
| 77 |
+
"tf_legacy_loss": false,
|
| 78 |
+
"tie_encoder_decoder": false,
|
| 79 |
+
"tie_word_embeddings": true,
|
| 80 |
+
"tokenizer_class": null,
|
| 81 |
+
"top_k": 50,
|
| 82 |
+
"top_p": 1.0,
|
| 83 |
+
"torch_dtype": null,
|
| 84 |
+
"torchscript": false,
|
| 85 |
+
"typical_p": 1.0,
|
| 86 |
+
"use_bfloat16": false,
|
| 87 |
+
"use_cache": true,
|
| 88 |
+
"vocab_size": 57606
|
| 89 |
+
},
|
| 90 |
+
"decoder_start_token_id": 57595,
|
| 91 |
+
"encoder": {
|
| 92 |
+
"_name_or_path": "",
|
| 93 |
+
"add_cross_attention": false,
|
| 94 |
+
"architectures": null,
|
| 95 |
+
"attention_probs_dropout_prob": 0.0,
|
| 96 |
+
"bad_words_ids": null,
|
| 97 |
+
"begin_suppress_tokens": null,
|
| 98 |
+
"bos_token_id": null,
|
| 99 |
+
"chunk_size_feed_forward": 0,
|
| 100 |
+
"cross_attention_hidden_size": null,
|
| 101 |
+
"decoder_start_token_id": null,
|
| 102 |
+
"depths": [
|
| 103 |
+
2,
|
| 104 |
+
2,
|
| 105 |
+
14,
|
| 106 |
+
2
|
| 107 |
+
],
|
| 108 |
+
"diversity_penalty": 0.0,
|
| 109 |
+
"do_sample": false,
|
| 110 |
+
"drop_path_rate": 0.1,
|
| 111 |
+
"early_stopping": false,
|
| 112 |
+
"embed_dim": 128,
|
| 113 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 114 |
+
"eos_token_id": null,
|
| 115 |
+
"exponential_decay_length_penalty": null,
|
| 116 |
+
"finetuning_task": null,
|
| 117 |
+
"forced_bos_token_id": null,
|
| 118 |
+
"forced_eos_token_id": null,
|
| 119 |
+
"hidden_act": "gelu",
|
| 120 |
+
"hidden_dropout_prob": 0.0,
|
| 121 |
+
"hidden_size": 1024,
|
| 122 |
+
"id2label": {
|
| 123 |
+
"0": "LABEL_0",
|
| 124 |
+
"1": "LABEL_1"
|
| 125 |
+
},
|
| 126 |
+
"image_size": [
|
| 127 |
+
1280,
|
| 128 |
+
960
|
| 129 |
+
],
|
| 130 |
+
"initializer_range": 0.02,
|
| 131 |
+
"is_decoder": false,
|
| 132 |
+
"is_encoder_decoder": false,
|
| 133 |
+
"label2id": {
|
| 134 |
+
"LABEL_0": 0,
|
| 135 |
+
"LABEL_1": 1
|
| 136 |
+
},
|
| 137 |
+
"layer_norm_eps": 1e-05,
|
| 138 |
+
"length_penalty": 1.0,
|
| 139 |
+
"max_length": 20,
|
| 140 |
+
"min_length": 0,
|
| 141 |
+
"mlp_ratio": 4.0,
|
| 142 |
+
"model_type": "donut-swin",
|
| 143 |
+
"no_repeat_ngram_size": 0,
|
| 144 |
+
"num_beam_groups": 1,
|
| 145 |
+
"num_beams": 1,
|
| 146 |
+
"num_channels": 3,
|
| 147 |
+
"num_heads": [
|
| 148 |
+
4,
|
| 149 |
+
8,
|
| 150 |
+
16,
|
| 151 |
+
32
|
| 152 |
+
],
|
| 153 |
+
"num_layers": 4,
|
| 154 |
+
"num_return_sequences": 1,
|
| 155 |
+
"output_attentions": false,
|
| 156 |
+
"output_hidden_states": false,
|
| 157 |
+
"output_scores": false,
|
| 158 |
+
"pad_token_id": null,
|
| 159 |
+
"patch_size": 4,
|
| 160 |
+
"path_norm": true,
|
| 161 |
+
"prefix": null,
|
| 162 |
+
"problem_type": null,
|
| 163 |
+
"pruned_heads": {},
|
| 164 |
+
"qkv_bias": true,
|
| 165 |
+
"remove_invalid_values": false,
|
| 166 |
+
"repetition_penalty": 1.0,
|
| 167 |
+
"return_dict": true,
|
| 168 |
+
"return_dict_in_generate": false,
|
| 169 |
+
"sep_token_id": null,
|
| 170 |
+
"suppress_tokens": null,
|
| 171 |
+
"task_specific_params": null,
|
| 172 |
+
"temperature": 1.0,
|
| 173 |
+
"tf_legacy_loss": false,
|
| 174 |
+
"tie_encoder_decoder": false,
|
| 175 |
+
"tie_word_embeddings": true,
|
| 176 |
+
"tokenizer_class": null,
|
| 177 |
+
"top_k": 50,
|
| 178 |
+
"top_p": 1.0,
|
| 179 |
+
"torch_dtype": null,
|
| 180 |
+
"torchscript": false,
|
| 181 |
+
"typical_p": 1.0,
|
| 182 |
+
"use_absolute_embeddings": false,
|
| 183 |
+
"use_bfloat16": false,
|
| 184 |
+
"window_size": 10
|
| 185 |
+
},
|
| 186 |
+
"is_encoder_decoder": true,
|
| 187 |
+
"model_type": "vision-encoder-decoder",
|
| 188 |
+
"pad_token_id": 1,
|
| 189 |
+
"tie_word_embeddings": false,
|
| 190 |
+
"torch_dtype": "float32",
|
| 191 |
+
"transformers_version": "4.35.0"
|
| 192 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 57595,
|
| 5 |
+
"eos_token_id": 2,
|
| 6 |
+
"forced_eos_token_id": 2,
|
| 7 |
+
"max_length": 768,
|
| 8 |
+
"pad_token_id": 1,
|
| 9 |
+
"transformers_version": "4.35.0"
|
| 10 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50f013ce5d259030560f05fafa5069a3953e2045c58b7fb1cc16df3a62e28cc5
|
| 3 |
+
size 809402520
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_align_long_axis": false,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_pad": true,
|
| 5 |
+
"do_rescale": true,
|
| 6 |
+
"do_resize": true,
|
| 7 |
+
"do_thumbnail": true,
|
| 8 |
+
"image_mean": [
|
| 9 |
+
0.5,
|
| 10 |
+
0.5,
|
| 11 |
+
0.5
|
| 12 |
+
],
|
| 13 |
+
"image_processor_type": "DonutImageProcessor",
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "DonutProcessor",
|
| 20 |
+
"resample": 2,
|
| 21 |
+
"rescale_factor": 0.00392156862745098,
|
| 22 |
+
"size": {
|
| 23 |
+
"height": 1280,
|
| 24 |
+
"width": 960
|
| 25 |
+
}
|
| 26 |
+
}
|
sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb9e3dce4c326195d08fc3dd0f7e2eee1da8595c847bf4c1a9c78b7a82d47e2d
|
| 3 |
+
size 1296245
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<s_document_series>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"content": "<s_issue_date>",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": false,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"content": "<s_issuer_ruc>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"content": "</s_issuer_ruc>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"content": "</s_document_number>",
|
| 33 |
+
"lstrip": false,
|
| 34 |
+
"normalized": false,
|
| 35 |
+
"rstrip": false,
|
| 36 |
+
"single_word": false
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"content": "</s_document_type>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"content": "</s_total>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"content": "</s_issue_date>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"content": "<s_document_type>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"content": "</s_document_series>",
|
| 68 |
+
"lstrip": false,
|
| 69 |
+
"normalized": false,
|
| 70 |
+
"rstrip": false,
|
| 71 |
+
"single_word": false
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"content": "<s_total>",
|
| 75 |
+
"lstrip": false,
|
| 76 |
+
"normalized": false,
|
| 77 |
+
"rstrip": false,
|
| 78 |
+
"single_word": false
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"content": "<s_document_number>",
|
| 82 |
+
"lstrip": false,
|
| 83 |
+
"normalized": false,
|
| 84 |
+
"rstrip": false,
|
| 85 |
+
"single_word": false
|
| 86 |
+
}
|
| 87 |
+
],
|
| 88 |
+
"bos_token": "<s>",
|
| 89 |
+
"cls_token": "<s>",
|
| 90 |
+
"eos_token": "</s>",
|
| 91 |
+
"mask_token": {
|
| 92 |
+
"content": "<mask>",
|
| 93 |
+
"lstrip": true,
|
| 94 |
+
"normalized": true,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false
|
| 97 |
+
},
|
| 98 |
+
"pad_token": "<pad>",
|
| 99 |
+
"sep_token": "</s>",
|
| 100 |
+
"unk_token": "<unk>"
|
| 101 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,749 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"57521": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": true,
|
| 38 |
+
"normalized": true,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"57522": {
|
| 44 |
+
"content": "<sep/>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": true,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": false
|
| 50 |
+
},
|
| 51 |
+
"57523": {
|
| 52 |
+
"content": "<s_iitcdip>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"57524": {
|
| 60 |
+
"content": "<s_synthdog>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"57525": {
|
| 68 |
+
"content": "<s_header>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": true,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": false
|
| 74 |
+
},
|
| 75 |
+
"57526": {
|
| 76 |
+
"content": "</s_header>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": true,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": false
|
| 82 |
+
},
|
| 83 |
+
"57527": {
|
| 84 |
+
"content": "<s_invoice_no>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": true,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": false
|
| 90 |
+
},
|
| 91 |
+
"57528": {
|
| 92 |
+
"content": "</s_invoice_no>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": true,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": false
|
| 98 |
+
},
|
| 99 |
+
"57529": {
|
| 100 |
+
"content": "<s_invoice_date>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": true,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": false
|
| 106 |
+
},
|
| 107 |
+
"57530": {
|
| 108 |
+
"content": "</s_invoice_date>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": true,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": false
|
| 114 |
+
},
|
| 115 |
+
"57531": {
|
| 116 |
+
"content": "<s_seller>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": true,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": false
|
| 122 |
+
},
|
| 123 |
+
"57532": {
|
| 124 |
+
"content": "</s_seller>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": true,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": false
|
| 130 |
+
},
|
| 131 |
+
"57533": {
|
| 132 |
+
"content": "<s_client>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": true,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": false
|
| 138 |
+
},
|
| 139 |
+
"57534": {
|
| 140 |
+
"content": "</s_client>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": true,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": false
|
| 146 |
+
},
|
| 147 |
+
"57535": {
|
| 148 |
+
"content": "<s_seller_tax_id>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": true,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": false
|
| 154 |
+
},
|
| 155 |
+
"57536": {
|
| 156 |
+
"content": "</s_seller_tax_id>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": true,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": false
|
| 162 |
+
},
|
| 163 |
+
"57537": {
|
| 164 |
+
"content": "<s_client_tax_id>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": true,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": false
|
| 170 |
+
},
|
| 171 |
+
"57538": {
|
| 172 |
+
"content": "</s_client_tax_id>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": true,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": false
|
| 178 |
+
},
|
| 179 |
+
"57539": {
|
| 180 |
+
"content": "<s_iban>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": true,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": false
|
| 186 |
+
},
|
| 187 |
+
"57540": {
|
| 188 |
+
"content": "</s_iban>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": true,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": false
|
| 194 |
+
},
|
| 195 |
+
"57541": {
|
| 196 |
+
"content": "<s_items>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": true,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": false
|
| 202 |
+
},
|
| 203 |
+
"57542": {
|
| 204 |
+
"content": "</s_items>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": true,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": false
|
| 210 |
+
},
|
| 211 |
+
"57543": {
|
| 212 |
+
"content": "<s_item_desc>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": true,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": false
|
| 218 |
+
},
|
| 219 |
+
"57544": {
|
| 220 |
+
"content": "</s_item_desc>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": true,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": false
|
| 226 |
+
},
|
| 227 |
+
"57545": {
|
| 228 |
+
"content": "<s_item_qty>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": true,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": false
|
| 234 |
+
},
|
| 235 |
+
"57546": {
|
| 236 |
+
"content": "</s_item_qty>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": true,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": false
|
| 242 |
+
},
|
| 243 |
+
"57547": {
|
| 244 |
+
"content": "<s_item_net_price>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": true,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": false
|
| 250 |
+
},
|
| 251 |
+
"57548": {
|
| 252 |
+
"content": "</s_item_net_price>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": true,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": false
|
| 258 |
+
},
|
| 259 |
+
"57549": {
|
| 260 |
+
"content": "<s_item_net_worth>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": true,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": false
|
| 266 |
+
},
|
| 267 |
+
"57550": {
|
| 268 |
+
"content": "</s_item_net_worth>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": true,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": false
|
| 274 |
+
},
|
| 275 |
+
"57551": {
|
| 276 |
+
"content": "<s_item_vat>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": true,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": false
|
| 282 |
+
},
|
| 283 |
+
"57552": {
|
| 284 |
+
"content": "</s_item_vat>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": true,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": false
|
| 290 |
+
},
|
| 291 |
+
"57553": {
|
| 292 |
+
"content": "<s_item_gross_worth>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": true,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": false
|
| 298 |
+
},
|
| 299 |
+
"57554": {
|
| 300 |
+
"content": "</s_item_gross_worth>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": true,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": false
|
| 306 |
+
},
|
| 307 |
+
"57555": {
|
| 308 |
+
"content": "<s_summary>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": true,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": false
|
| 314 |
+
},
|
| 315 |
+
"57556": {
|
| 316 |
+
"content": "</s_summary>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": true,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": false
|
| 322 |
+
},
|
| 323 |
+
"57557": {
|
| 324 |
+
"content": "<s_total_net_worth>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": true,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": false
|
| 330 |
+
},
|
| 331 |
+
"57558": {
|
| 332 |
+
"content": "</s_total_net_worth>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": true,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": false
|
| 338 |
+
},
|
| 339 |
+
"57559": {
|
| 340 |
+
"content": "<s_total_vat>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": true,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": false
|
| 346 |
+
},
|
| 347 |
+
"57560": {
|
| 348 |
+
"content": "</s_total_vat>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": true,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": false
|
| 354 |
+
},
|
| 355 |
+
"57561": {
|
| 356 |
+
"content": "<s_total_gross_worth>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": true,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": false
|
| 362 |
+
},
|
| 363 |
+
"57562": {
|
| 364 |
+
"content": "</s_total_gross_worth>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": true,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": false
|
| 370 |
+
},
|
| 371 |
+
"57563": {
|
| 372 |
+
"content": "<s_None>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": true,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": false
|
| 378 |
+
},
|
| 379 |
+
"57564": {
|
| 380 |
+
"content": "</s_None>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": true,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": false
|
| 386 |
+
},
|
| 387 |
+
"57565": {
|
| 388 |
+
"content": "<s_store_name>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": true,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": false
|
| 394 |
+
},
|
| 395 |
+
"57566": {
|
| 396 |
+
"content": "</s_store_name>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": true,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": false
|
| 402 |
+
},
|
| 403 |
+
"57567": {
|
| 404 |
+
"content": "<s_store_addr>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": true,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": false
|
| 410 |
+
},
|
| 411 |
+
"57568": {
|
| 412 |
+
"content": "</s_store_addr>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": true,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": false
|
| 418 |
+
},
|
| 419 |
+
"57569": {
|
| 420 |
+
"content": "<s_telephone>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": true,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": false
|
| 426 |
+
},
|
| 427 |
+
"57570": {
|
| 428 |
+
"content": "</s_telephone>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": true,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": false
|
| 434 |
+
},
|
| 435 |
+
"57571": {
|
| 436 |
+
"content": "<s_date>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": true,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": false
|
| 442 |
+
},
|
| 443 |
+
"57572": {
|
| 444 |
+
"content": "</s_date>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": true,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": false
|
| 450 |
+
},
|
| 451 |
+
"57573": {
|
| 452 |
+
"content": "<s_time>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": true,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": false
|
| 458 |
+
},
|
| 459 |
+
"57574": {
|
| 460 |
+
"content": "</s_time>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": true,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": false
|
| 466 |
+
},
|
| 467 |
+
"57575": {
|
| 468 |
+
"content": "<s_subtotal>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": true,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": false
|
| 474 |
+
},
|
| 475 |
+
"57576": {
|
| 476 |
+
"content": "</s_subtotal>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": true,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": false
|
| 482 |
+
},
|
| 483 |
+
"57577": {
|
| 484 |
+
"content": "<s_tax>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": true,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": false
|
| 490 |
+
},
|
| 491 |
+
"57578": {
|
| 492 |
+
"content": "</s_tax>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": true,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": false
|
| 498 |
+
},
|
| 499 |
+
"57579": {
|
| 500 |
+
"content": "<s_total>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"57580": {
|
| 508 |
+
"content": "</s_total>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"57581": {
|
| 516 |
+
"content": "<s_ignore>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": true,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": false
|
| 522 |
+
},
|
| 523 |
+
"57582": {
|
| 524 |
+
"content": "</s_ignore>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": true,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": false
|
| 530 |
+
},
|
| 531 |
+
"57583": {
|
| 532 |
+
"content": "<s_tips>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": true,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": false
|
| 538 |
+
},
|
| 539 |
+
"57584": {
|
| 540 |
+
"content": "</s_tips>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": true,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": false
|
| 546 |
+
},
|
| 547 |
+
"57585": {
|
| 548 |
+
"content": "<s_line_items>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": true,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": false
|
| 554 |
+
},
|
| 555 |
+
"57586": {
|
| 556 |
+
"content": "</s_line_items>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": true,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": false
|
| 562 |
+
},
|
| 563 |
+
"57587": {
|
| 564 |
+
"content": "<s_item_key>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": true,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": false
|
| 570 |
+
},
|
| 571 |
+
"57588": {
|
| 572 |
+
"content": "</s_item_key>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": true,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": false
|
| 578 |
+
},
|
| 579 |
+
"57589": {
|
| 580 |
+
"content": "<s_item_name>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": true,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": false
|
| 586 |
+
},
|
| 587 |
+
"57590": {
|
| 588 |
+
"content": "</s_item_name>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": true,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": false
|
| 594 |
+
},
|
| 595 |
+
"57591": {
|
| 596 |
+
"content": "<s_item_value>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": true,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": false
|
| 602 |
+
},
|
| 603 |
+
"57592": {
|
| 604 |
+
"content": "</s_item_value>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": true,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": false
|
| 610 |
+
},
|
| 611 |
+
"57593": {
|
| 612 |
+
"content": "<s_item_quantity>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": true,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": false
|
| 618 |
+
},
|
| 619 |
+
"57594": {
|
| 620 |
+
"content": "</s_item_quantity>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": true,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": false
|
| 626 |
+
},
|
| 627 |
+
"57595": {
|
| 628 |
+
"content": "<s_receipt>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": true,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": false
|
| 634 |
+
},
|
| 635 |
+
"57596": {
|
| 636 |
+
"content": "<s_document_series>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"57597": {
|
| 644 |
+
"content": "<s_issue_date>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"57598": {
|
| 652 |
+
"content": "<s_issuer_ruc>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"57599": {
|
| 660 |
+
"content": "</s_issuer_ruc>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"57600": {
|
| 668 |
+
"content": "</s_document_number>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"57601": {
|
| 676 |
+
"content": "</s_document_type>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"57602": {
|
| 684 |
+
"content": "</s_issue_date>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"57603": {
|
| 692 |
+
"content": "<s_document_type>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"57604": {
|
| 700 |
+
"content": "</s_document_series>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"57605": {
|
| 708 |
+
"content": "<s_document_number>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
}
|
| 715 |
+
},
|
| 716 |
+
"additional_special_tokens": [
|
| 717 |
+
"<s_document_series>",
|
| 718 |
+
"<s_issue_date>",
|
| 719 |
+
"<s_issuer_ruc>",
|
| 720 |
+
"</s_issuer_ruc>",
|
| 721 |
+
"</s_document_number>",
|
| 722 |
+
"</s_document_type>",
|
| 723 |
+
"</s_total>",
|
| 724 |
+
"</s_issue_date>",
|
| 725 |
+
"<s_document_type>",
|
| 726 |
+
"</s_document_series>",
|
| 727 |
+
"<s_total>",
|
| 728 |
+
"<s_document_number>"
|
| 729 |
+
],
|
| 730 |
+
"bos_token": "<s>",
|
| 731 |
+
"clean_up_tokenization_spaces": true,
|
| 732 |
+
"cls_token": "<s>",
|
| 733 |
+
"eos_token": "</s>",
|
| 734 |
+
"mask_token": "<mask>",
|
| 735 |
+
"max_length": 768,
|
| 736 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 737 |
+
"pad_to_multiple_of": null,
|
| 738 |
+
"pad_token": "<pad>",
|
| 739 |
+
"pad_token_type_id": 0,
|
| 740 |
+
"padding_side": "right",
|
| 741 |
+
"processor_class": "DonutProcessor",
|
| 742 |
+
"sep_token": "</s>",
|
| 743 |
+
"sp_model_kwargs": {},
|
| 744 |
+
"stride": 0,
|
| 745 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 746 |
+
"truncation_side": "right",
|
| 747 |
+
"truncation_strategy": "longest_first",
|
| 748 |
+
"unk_token": "<unk>"
|
| 749 |
+
}
|