Upload 11 files

README.md

@@ -1,3 +1,168 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+---
+
+Model Architecture:
+
+The mychen76/invoice-and-receipts_donut_v1 (LLM) is a finetuned for convert Invoice or Receipt Image to XML or Json data strucutre task. this experimental model is based on Donut model.
+
+Motivation:
+
+Remove OCR engine, use only LLM model to convert an invoice or receipt json object could reduce the conversion step and reduce resource utilization and deployment dependencies. Result, better performance.
+
+Model Usage:
+
+Take following an invoice receipt image and get an output Json or xml like this:
+
+***JSON OUTPUT***
+```json
+
+{
+    'header': {
+        'invoice_no': '13194726',
+        'invoice_date': '05/29/2021',
+        'seller': 'Hopkins and Sons 62283 Flores Tunnel North Luis, IA 69983',
+        'client': 'Sims PLC USS Kramer FPO AA 81651',
+        'seller_tax_id': '952-73-7223',
+        'client_tax_id': '995-88-9495',
+        'iban': 'GB31LZX520242755934691'
+    },
+    'items': [
+        {
+            'item_desc': 'Beach Lunch Lounge Striped Shirt Dress Large Navy Blue White Long Sleeve Casual',
+            'item_qty': '1,00',
+            'item_net_price': '16,99',
+            'item_net_worth': '16,99',
+            'item_vat': '10%',
+            'item_gross_worth': '18,69'
+        },
+        {
+            'item_desc': 'Jams World Hawaiian 0 Dress Rayon SZ.L',
+            'item_qty': '5,00',
+            'item_net_price': '65,00',
+            'item_net_worth': '325,00',
+            'item_vat': '10%',
+            'item_gross_worth': '357,50'
+        },
+        {
+            'item_desc': 'LuLaRoe Nicole Dress Size Large 26',
+            'item_qty': '2,00',
+            'item_net_price': '1,99',
+            'item_net_worth': '3,98',
+            'item_vat': '10%',
+            'item_gross_worth': '4,38'
+        },
+        {
+            'item_desc': 'phynny Was Medium Linen Wrap Dress Dessert Rose Embroidered Bohemian',
+            'item_qty': '2,00',
+            'item_net_price': '89,99',
+            'item_net_worth': '179,98',
+            'item_vat': '10%',
+            'item_gross_worth': '197,98'
+        },
+        {
+            'item_desc': "Eileen Fisher Women's Long Sleeve Fleece Lined Front Pockets Dress XS Gray",
+            'item_qty': '2,00',
+            'item_net_price': '15,99',
+            'item_net_worth': '31,98',
+            'item_vat': '10%',
+            'item_gross_worth': '35,18'
+        },
+        {
+            'item_desc': "Hanna Anderson Women's L Large Coral Short Sleeve Casual Fall Tee Shirt Dress",
+            'item_qty': '1,00',
+            'item_net_price': '24,00',
+            'item_net_worth': '24,00',
+            'item_vat': '10%',
+            'item_gross_worth': '26,40'
+        }
+    ],
+    'summary': {'total_net_worth': '$581,93', 'total_vat': '$58,19', 'total_gross_worth': '$ 640,12'}
+}
+
+```
+
+***XML OUTPUT***
+
+```xml
+<s_header>
+    <s_invoice_no> 13194726</s_invoice_no>
+    <s_invoice_date> 05/29/2021</s_invoice_date>
+    <s_seller> Hopkins and 
+    Sons 62283 Flores Tunnel North Luis, IA 69983</s_seller>
+    <s_client> Sims PLC USS Kramer FPO AA 
+    81651</s_client>
+    <s_seller_tax_id> 952-73-7223</s_seller_tax_id>
+    <s_client_tax_id> 
+    995-88-9495</s_client_tax_id>
+    <s_iban> GB31LZX520242755934691</s_iban>
+</s_header>
+<s_items>
+    <s_item_desc> Beach Lunch 
+    Lounge Striped Shirt Dress Large Navy Blue White Long Sleeve Casual</s_item_desc>
+    <s_item_qty> 
+    1,00</s_item_qty>
+    <s_item_net_price> 16,99</s_item_net_price>
+    <s_item_net_worth> 16,99</s_item_net_worth>
+    <s_item_vat>
+    10%</s_item_vat>
+    <s_item_gross_worth> 18,69</s_item_gross_worth>
+    <sep/>
+    <s_item_desc> Jams World Hawaiian 0 Dress 
+    Rayon SZ.L</s_item_desc>
+    <s_item_qty> 5,00</s_item_qty>
+    <s_item_net_price> 65,00</s_item_net_price>
+    <s_item_net_worth>
+    325,00</s_item_net_worth>
+    <s_item_vat> 10%</s_item_vat>
+    <s_item_gross_worth> 
+    357,50</s_item_gross_worth>
+    <sep/>
+    <s_item_desc> LuLaRoe Nicole Dress Size Large 26</s_item_desc>
+    <s_item_qty> 
+    2,00</s_item_qty>
+    <s_item_net_price> 1,99</s_item_net_price>
+    <s_item_net_worth> 3,98</s_item_net_worth>
+    <s_item_vat> 
+    10%</s_item_vat>
+    <s_item_gross_worth> 4,38</s_item_gross_worth>
+    <sep/>
+    <s_item_desc> phynny Was Medium Linen Wrap 
+    Dress Dessert Rose Embroidered Bohemian</s_item_desc>
+    <s_item_qty> 2,00</s_item_qty>
+    <s_item_net_price> 
+    89,99</s_item_net_price>
+    <s_item_net_worth> 179,98</s_item_net_worth>
+    <s_item_vat> 
+    10%</s_item_vat>
+    <s_item_gross_worth> 197,98</s_item_gross_worth>
+    <sep/>
+    <s_item_desc> Eileen Fisher Women's Long 
+    Sleeve Fleece Lined Front Pockets Dress XS Gray</s_item_desc>
+    <s_item_qty> 2,00</s_item_qty>
+    <s_item_net_price> 
+    15,99</s_item_net_price>
+    <s_item_net_worth> 31,98</s_item_net_worth>
+    <s_item_vat> 
+    10%</s_item_vat>
+    <s_item_gross_worth> 35,18</s_item_gross_worth>
+    <sep/>
+    <s_item_desc> Hanna Anderson Women's L Large 
+    Coral Short Sleeve Casual Fall Tee Shirt Dress</s_item_desc>
+    <s_item_qty> 1,00</s_item_qty>
+    <s_item_net_price> 
+    24,00</s_item_net_price>
+    <s_item_net_worth> 24,00</s_item_net_worth>
+    <s_item_vat> 
+    10%</s_item_vat>
+    <s_item_gross_worth> 26,40</s_item_gross_worth>
+</s_items>
+<s_summary>
+    <s_total_net_worth> 
+    $581,93</s_total_net_worth>
+    <s_total_vat> $58,19</s_total_vat>
+    <s_total_gross_worth> $ 
+    640,12</s_total_gross_worth>
+</s_summary>
+
+```

added_tokens.json

@@ -0,0 +1,76 @@
+{
+  "</s_None>": 57564,
+  "</s_client>": 57534,
+  "</s_client_tax_id>": 57538,
+  "</s_date>": 57572,
+  "</s_header>": 57526,
+  "</s_iban>": 57540,
+  "</s_ignore>": 57582,
+  "</s_invoice_date>": 57530,
+  "</s_invoice_no>": 57528,
+  "</s_item_desc>": 57544,
+  "</s_item_gross_worth>": 57554,
+  "</s_item_key>": 57588,
+  "</s_item_name>": 57590,
+  "</s_item_net_price>": 57548,
+  "</s_item_net_worth>": 57550,
+  "</s_item_qty>": 57546,
+  "</s_item_quantity>": 57594,
+  "</s_item_value>": 57592,
+  "</s_item_vat>": 57552,
+  "</s_items>": 57542,
+  "</s_line_items>": 57586,
+  "</s_seller>": 57532,
+  "</s_seller_tax_id>": 57536,
+  "</s_store_addr>": 57568,
+  "</s_store_name>": 57566,
+  "</s_subtotal>": 57576,
+  "</s_summary>": 57556,
+  "</s_tax>": 57578,
+  "</s_telephone>": 57570,
+  "</s_time>": 57574,
+  "</s_tips>": 57584,
+  "</s_total>": 57580,
+  "</s_total_gross_worth>": 57562,
+  "</s_total_net_worth>": 57558,
+  "</s_total_vat>": 57560,
+  "<s_None>": 57563,
+  "<s_client>": 57533,
+  "<s_client_tax_id>": 57537,
+  "<s_date>": 57571,
+  "<s_header>": 57525,
+  "<s_iban>": 57539,
+  "<s_ignore>": 57581,
+  "<s_iitcdip>": 57523,
+  "<s_invoice_date>": 57529,
+  "<s_invoice_no>": 57527,
+  "<s_item_desc>": 57543,
+  "<s_item_gross_worth>": 57553,
+  "<s_item_key>": 57587,
+  "<s_item_name>": 57589,
+  "<s_item_net_price>": 57547,
+  "<s_item_net_worth>": 57549,
+  "<s_item_qty>": 57545,
+  "<s_item_quantity>": 57593,
+  "<s_item_value>": 57591,
+  "<s_item_vat>": 57551,
+  "<s_items>": 57541,
+  "<s_line_items>": 57585,
+  "<s_receipt>": 57595,
+  "<s_seller>": 57531,
+  "<s_seller_tax_id>": 57535,
+  "<s_store_addr>": 57567,
+  "<s_store_name>": 57565,
+  "<s_subtotal>": 57575,
+  "<s_summary>": 57555,
+  "<s_synthdog>": 57524,
+  "<s_tax>": 57577,
+  "<s_telephone>": 57569,
+  "<s_time>": 57573,
+  "<s_tips>": 57583,
+  "<s_total>": 57579,
+  "<s_total_gross_worth>": 57561,
+  "<s_total_net_worth>": 57557,
+  "<s_total_vat>": 57559,
+  "<sep/>": 57522
+}

config.json

@@ -0,0 +1,192 @@
+{
+  "_name_or_path": "naver-clova-ix/donut-base",
+  "architectures": [
+    "VisionEncoderDecoderModel"
+  ],
+  "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,
+    "begin_suppress_tokens": 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": 768,
+    "max_position_embeddings": 1536,
+    "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,
+    "suppress_tokens": 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,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 57596
+  },
+  "decoder_start_token_id": 57595,
+  "encoder": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_probs_dropout_prob": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": 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,
+    "suppress_tokens": 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,
+    "typical_p": 1.0,
+    "use_absolute_embeddings": false,
+    "use_bfloat16": false,
+    "window_size": 10
+  },
+  "is_encoder_decoder": true,
+  "model_type": "vision-encoder-decoder",
+  "pad_token_id": 1,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0.dev0"
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 57595,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "max_length": 768,
+  "pad_token_id": 1,
+  "transformers_version": "4.34.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6244552088eda89a0bb82c1b42e86340271ebd68e420d0920d9be83d38fe7a7d
+size 809361616

preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "do_align_long_axis": false,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_thumbnail": true,
+  "feature_extractor_type": "DonutFeatureExtractor",
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "DonutImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "DonutProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": [
+    960,
+    1280
+  ]
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebe7d377a60345bd02a7572f4f04053ad5504cc21ef32ef05a5b9fef13ee957f
+size 809469721

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb9e3dce4c326195d08fc3dd0f7e2eee1da8595c847bf4c1a9c78b7a82d47e2d
+size 1296245

special_tokens_map.json

@@ -0,0 +1,19 @@
+{
+  "additional_special_tokens": [
+    "<s_iitcdip>",
+    "<s_synthdog>"
+  ],
+  "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

@@ -0,0 +1,21 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "processor_class": "DonutProcessor",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}