Training done

added_tokens.json

@@ -0,0 +1,82 @@
+{
+  "</s_Amount>": 57538,
+  "</s_AmountDue>": 57560,
+  "</s_BillingAddress>": 57586,
+  "</s_BillingAddressRecipient>": 57584,
+  "</s_CustomerAddress>": 57532,
+  "</s_CustomerAddressRecipient>": 57534,
+  "</s_CustomerId>": 57558,
+  "</s_CustomerName>": 57530,
+  "</s_CustomerTaxId>": 57594,
+  "</s_Description>": 57542,
+  "</s_DueDate>": 57568,
+  "</s_InvoiceDate>": 57536,
+  "</s_InvoiceId>": 57544,
+  "</s_InvoiceTotal>": 57546,
+  "</s_ItemDate>": 57590,
+  "</s_ItemLines>": 57540,
+  "</s_ItemTax>": 57572,
+  "</s_ItemUnit>": 57562,
+  "</s_PaymentTerm>": 57550,
+  "</s_PreviousUnpaidBalance>": 57598,
+  "</s_ProductCode>": 57582,
+  "</s_PurchaseOrder>": 57552,
+  "</s_Quantity>": 57554,
+  "</s_RemittanceAddress>": 57548,
+  "</s_RemittanceAddressRecipient>": 57578,
+  "</s_ServiceAddress>": 57592,
+  "</s_ServiceAddressRecipient>": 57600,
+  "</s_ServiceEndDate>": 57576,
+  "</s_ServiceStartDate>": 57574,
+  "</s_ShippingAddress>": 57564,
+  "</s_ShippingAddressRecipient>": 57566,
+  "</s_SubTotal>": 57570,
+  "</s_TotalTax>": 57596,
+  "</s_UnitPrice>": 57556,
+  "</s_VendorAddress>": 57528,
+  "</s_VendorAddressRecipient>": 57580,
+  "</s_VendorName>": 57526,
+  "</s_VendorTaxId>": 57588,
+  "<s_Amount>": 57537,
+  "<s_AmountDue>": 57559,
+  "<s_BillingAddress>": 57585,
+  "<s_BillingAddressRecipient>": 57583,
+  "<s_CustomerAddress>": 57531,
+  "<s_CustomerAddressRecipient>": 57533,
+  "<s_CustomerId>": 57557,
+  "<s_CustomerName>": 57529,
+  "<s_CustomerTaxId>": 57593,
+  "<s_Description>": 57541,
+  "<s_DueDate>": 57567,
+  "<s_InvoiceDate>": 57535,
+  "<s_InvoiceId>": 57543,
+  "<s_InvoiceTotal>": 57545,
+  "<s_ItemDate>": 57589,
+  "<s_ItemLines>": 57539,
+  "<s_ItemTax>": 57571,
+  "<s_ItemUnit>": 57561,
+  "<s_PaymentTerm>": 57549,
+  "<s_PreviousUnpaidBalance>": 57597,
+  "<s_ProductCode>": 57581,
+  "<s_PurchaseOrder>": 57551,
+  "<s_Quantity>": 57553,
+  "<s_RemittanceAddress>": 57547,
+  "<s_RemittanceAddressRecipient>": 57577,
+  "<s_ServiceAddress>": 57591,
+  "<s_ServiceAddressRecipient>": 57599,
+  "<s_ServiceEndDate>": 57575,
+  "<s_ServiceStartDate>": 57573,
+  "<s_ShippingAddress>": 57563,
+  "<s_ShippingAddressRecipient>": 57565,
+  "<s_SubTotal>": 57569,
+  "<s_TotalTax>": 57595,
+  "<s_UnitPrice>": 57555,
+  "<s_VendorAddress>": 57527,
+  "<s_VendorAddressRecipient>": 57579,
+  "<s_VendorName>": 57525,
+  "<s_VendorTaxId>": 57587,
+  "<s_iitcdip>": 57523,
+  "<s_synthdog>": 57524,
+  "<s_unstructured-invoices>": 57601,
+  "<sep/>": 57522
+}

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "do_align_long_axis": false,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_thumbnail": true,
+  "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
+  ]
+}

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 +1,22 @@
+{
+  "bos_token": "<s>",
+  "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,
+  "name_or_path": "nielsr/donut-base",
+  "pad_token": "<pad>",
+  "processor_class": "DonutProcessor",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}