Add files

.gitignore

@@ -0,0 +1 @@
+.DS_Store

README.md

@@ -1,3 +0,0 @@
----
-license: mit
----

added_tokens.json

@@ -1 +1,68 @@
-{"<sep/>": 57522, "<s_iitcdip>": 57523, "<s_synthdog>": 57524, "</s_menu>": 57525, "<s_menu>": 57526, "</s_nm>": 57527, "<s_nm>": 57528, "</s_cnt>": 57529, "<s_cnt>": 57530, "</s_price>": 57531, "<s_price>": 57532, "</s_sub_total>": 57533, "<s_sub_total>": 57534, "</s_subtotal_price>": 57535, "<s_subtotal_price>": 57536, "</s_service_price>": 57537, "<s_service_price>": 57538, "</s_tax_price>": 57539, "<s_tax_price>": 57540, "</s_etc>": 57541, "<s_etc>": 57542, "</s_total>": 57543, "<s_total>": 57544, "</s_total_price>": 57545, "<s_total_price>": 57546, "</s_sub_nm>": 57547, "<s_sub_nm>": 57548, "</s_cashprice>": 57549, "<s_cashprice>": 57550, "</s_changeprice>": 57551, "<s_changeprice>": 57552, "</s_menutype_cnt>": 57553, "<s_menutype_cnt>": 57554, "</s_menuqty_cnt>": 57555, "<s_menuqty_cnt>": 57556, "</s_discount_price>": 57557, "<s_discount_price>": 57558, "</s_unitprice>": 57559, "<s_unitprice>": 57560, "</s_total_etc>": 57561, "<s_total_etc>": 57562, "</s_creditcardprice>": 57563, "<s_creditcardprice>": 57564, "</s_num>": 57565, "<s_num>": 57566, "</s_sub_cnt>": 57567, "<s_sub_cnt>": 57568, "</s_discountprice>": 57569, "<s_discountprice>": 57570, "</s_sub_price>": 57571, "<s_sub_price>": 57572, "</s_emoneyprice>": 57573, "<s_emoneyprice>": 57574, "</s_sub_unitprice>": 57575, "<s_sub_unitprice>": 57576, "</s_sub_etc>": 57577, "<s_sub_etc>": 57578, "</s_void_menu>": 57579, "<s_void_menu>": 57580, "</s_othersvc_price>": 57581, "<s_othersvc_price>": 57582, "</s_vatyn>": 57583, "<s_vatyn>": 57584, "</s_itemsubtotal>": 57585, "<s_itemsubtotal>": 57586, "<s_cord-v1>": 57587}
+{
+  "</s_cashprice>": 57549,
+  "</s_changeprice>": 57551,
+  "</s_cnt>": 57529,
+  "</s_creditcardprice>": 57563,
+  "</s_discount_price>": 57557,
+  "</s_discountprice>": 57569,
+  "</s_emoneyprice>": 57573,
+  "</s_etc>": 57541,
+  "</s_itemsubtotal>": 57585,
+  "</s_menu>": 57525,
+  "</s_menuqty_cnt>": 57555,
+  "</s_menutype_cnt>": 57553,
+  "</s_nm>": 57527,
+  "</s_num>": 57565,
+  "</s_othersvc_price>": 57581,
+  "</s_price>": 57531,
+  "</s_service_price>": 57537,
+  "</s_sub_cnt>": 57567,
+  "</s_sub_etc>": 57577,
+  "</s_sub_nm>": 57547,
+  "</s_sub_price>": 57571,
+  "</s_sub_total>": 57533,
+  "</s_sub_unitprice>": 57575,
+  "</s_subtotal_price>": 57535,
+  "</s_tax_price>": 57539,
+  "</s_total>": 57543,
+  "</s_total_etc>": 57561,
+  "</s_total_price>": 57545,
+  "</s_unitprice>": 57559,
+  "</s_vatyn>": 57583,
+  "</s_void_menu>": 57579,
+  "<s_cashprice>": 57550,
+  "<s_changeprice>": 57552,
+  "<s_cnt>": 57530,
+  "<s_cord-v1>": 57587,
+  "<s_creditcardprice>": 57564,
+  "<s_discount_price>": 57558,
+  "<s_discountprice>": 57570,
+  "<s_emoneyprice>": 57574,
+  "<s_etc>": 57542,
+  "<s_iitcdip>": 57523,
+  "<s_itemsubtotal>": 57586,
+  "<s_menu>": 57526,
+  "<s_menuqty_cnt>": 57556,
+  "<s_menutype_cnt>": 57554,
+  "<s_nm>": 57528,
+  "<s_num>": 57566,
+  "<s_othersvc_price>": 57582,
+  "<s_price>": 57532,
+  "<s_service_price>": 57538,
+  "<s_sub_cnt>": 57568,
+  "<s_sub_etc>": 57578,
+  "<s_sub_nm>": 57548,
+  "<s_sub_price>": 57572,
+  "<s_sub_total>": 57534,
+  "<s_sub_unitprice>": 57576,
+  "<s_subtotal_price>": 57536,
+  "<s_synthdog>": 57524,
+  "<s_tax_price>": 57540,
+  "<s_total>": 57544,
+  "<s_total_etc>": 57562,
+  "<s_total_price>": 57546,
+  "<s_unitprice>": 57560,
+  "<s_vatyn>": 57584,
+  "<s_void_menu>": 57580,
+  "<sep/>": 57522
+}

config.json

@@ -1,24 +1,188 @@
 {
-  "_name_or_path": "naver-clova-ix/donut-base",
-  "align_long_axis": false,
+  "_commit_hash": null,
   "architectures": [
-    "DonutModel"
+    "VisionEncoderDecoderModel"
   ],
-  "decoder_layer": 4,
-  "encoder_layer": [
-    2,
-    2,
-    14,
-    2
-  ],
-  "input_size": [
-    1280,
-    960
-  ],
-  "max_length": 768,
-  "max_position_embeddings": 768,
-  "model_type": "donut",
+  "decoder": {
+    "_name_or_path": "",
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "add_cross_attention": true,
+    "add_final_layer_norm": true,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": 0.0,
+    "cross_attention_hidden_size": null,
+    "d_model": 1024,
+    "decoder_attention_heads": 16,
+    "decoder_ffn_dim": 4096,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 4,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "encoder_attention_heads": 16,
+    "encoder_ffn_dim": 4096,
+    "encoder_layerdrop": 0.0,
+    "encoder_layers": 12,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": 2,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "init_std": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 768,
+    "min_length": 0,
+    "model_type": "mbart",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_embedding": true,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.22.0.dev0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 57588
+  },
+  "encoder": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_probs_dropout_prob": 0.0,
+    "bad_words_ids": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "depths": [
+      2,
+      2,
+      14,
+      2
+    ],
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "drop_path_rate": 0.1,
+    "early_stopping": false,
+    "embed_dim": 128,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": [
+      1280,
+      960
+    ],
+    "initializer_range": 0.02,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "mlp_ratio": 4.0,
+    "model_type": "donut-swin",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_heads": [
+      4,
+      8,
+      16,
+      32
+    ],
+    "num_layers": 4,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 4,
+    "path_norm": true,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "qkv_bias": true,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.22.0.dev0",
+    "typical_p": 1.0,
+    "use_absolute_embeddings": false,
+    "use_bfloat16": false,
+    "window_size": 10
+  },
+  "is_encoder_decoder": true,
+  "model_type": "vision-encoder-decoder",
+  "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.11.3",
-  "window_size": 10
+  "transformers_version": null
 }

preprocessor_config.json

@@ -0,0 +1,24 @@
+{
+  "do_align_long_axis": false,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_resize": true,
+  "do_thumbnail": true,
+  "feature_extractor_type": "DonutFeatureExtractor",
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "DonutProcessor",
+  "resample": 2,
+  "size": [
+    960,
+    1280
+  ]
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6d20983fbce7d629183b320bd00fa5953a816cb867759106049d523d670677c
-size 858616323
+oid sha256:187e924cdf3b46716cfdbfeb891353a76c32ce79b2eb987c59b54063be06fa02
+size 806281019

special_tokens_map.json

@@ -1 +1,18 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, "additional_special_tokens": ["<s_cord-v1>"]}
+{
+  "additional_special_tokens": [
+    "<s_cord-v1>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -1 +1,22 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "special_tokens_map_file": null, "tokenizer_file": "/root/.cache/huggingface/transformers/213c2041358e63047b407f94cde1ae23904d31a3bceb57eab291028c1e949437.7135a4b25ac726e19641f0d68803ff02bad960d6319064f55fa9c536929b86fc", "name_or_path": "/mnt/ocr-nfsx1/donut/pretrained_models_hf_format/donut-base", "tokenizer_class": "XLMRobertaTokenizer"}
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "from_slow": true,
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "name_or_path": "naver-clova-ix/donut-base-finetuned-cord-v1",
+  "pad_token": "<pad>",
+  "processor_class": "DonutProcessor",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}