First commit

config.json

@@ -0,0 +1,94 @@
+{
+  "architectures": [
+    "LayoutLMv3ForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "coordinate_size": 128,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "has_relative_attention_bias": true,
+  "has_spatial_attention_bias": true,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-INVOICE_NUMBER",
+    "2": "I-INVOICE_NUMBER",
+    "3": "B-DATE",
+    "4": "I-DATE",
+    "5": "B-VENDOR_NAME",
+    "6": "I-VENDOR_NAME",
+    "7": "B-VENDOR_ADDRESS",
+    "8": "I-VENDOR_ADDRESS",
+    "9": "B-CUSTOMER_NAME",
+    "10": "I-CUSTOMER_NAME",
+    "11": "B-CUSTOMER_ADDRESS",
+    "12": "I-CUSTOMER_ADDRESS",
+    "13": "B-ITEM_NAME",
+    "14": "I-ITEM_NAME",
+    "15": "B-QUANTITY",
+    "16": "I-QUANTITY",
+    "17": "B-UNIT_PRICE",
+    "18": "I-UNIT_PRICE",
+    "19": "B-LINE_AMOUNT",
+    "20": "I-LINE_AMOUNT",
+    "21": "B-TOTAL_AMOUNT",
+    "22": "I-TOTAL_AMOUNT",
+    "23": "B-TAX_AMOUNT",
+    "24": "I-TAX_AMOUNT"
+  },
+  "initializer_range": 0.02,
+  "input_size": 224,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-CUSTOMER_ADDRESS": 11,
+    "B-CUSTOMER_NAME": 9,
+    "B-DATE": 3,
+    "B-INVOICE_NUMBER": 1,
+    "B-ITEM_NAME": 13,
+    "B-LINE_AMOUNT": 19,
+    "B-QUANTITY": 15,
+    "B-TAX_AMOUNT": 23,
+    "B-TOTAL_AMOUNT": 21,
+    "B-UNIT_PRICE": 17,
+    "B-VENDOR_ADDRESS": 7,
+    "B-VENDOR_NAME": 5,
+    "I-CUSTOMER_ADDRESS": 12,
+    "I-CUSTOMER_NAME": 10,
+    "I-DATE": 4,
+    "I-INVOICE_NUMBER": 2,
+    "I-ITEM_NAME": 14,
+    "I-LINE_AMOUNT": 20,
+    "I-QUANTITY": 16,
+    "I-TAX_AMOUNT": 24,
+    "I-TOTAL_AMOUNT": 22,
+    "I-UNIT_PRICE": 18,
+    "I-VENDOR_ADDRESS": 8,
+    "I-VENDOR_NAME": 6,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_2d_position_embeddings": 1024,
+  "max_position_embeddings": 514,
+  "max_rel_2d_pos": 256,
+  "max_rel_pos": 128,
+  "model_type": "layoutlmv3",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "patch_size": 16,
+  "rel_2d_pos_bins": 64,
+  "rel_pos_bins": 32,
+  "second_input_size": 112,
+  "shape_size": 128,
+  "text_embed": true,
+  "transformers_version": "5.3.0",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "visual_embed": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:109c06a939584814bf5d3475e6fa0284f26462c48937c65578a5761db232cfcb
+size 503773476

processor_config.json

@@ -0,0 +1,28 @@
+{
+  "image_processor": {
+    "apply_ocr": false,
+    "data_format": "channels_first",
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "LayoutLMv3ImageProcessorFast",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "resample": 2,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "height": 224,
+      "width": 224
+    },
+    "tesseract_config": ""
+  },
+  "processor_class": "LayoutLMv3Processor"
+}

tokenizer_config.json

@@ -0,0 +1,37 @@
+{
+  "add_prefix_space": true,
+  "apply_ocr": false,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "cls_token_box": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "eos_token": "</s>",
+  "errors": "replace",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "only_label_first_subword": true,
+  "pad_token": "<pad>",
+  "pad_token_box": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "pad_token_label": -100,
+  "processor_class": "LayoutLMv3Processor",
+  "sep_token": "</s>",
+  "sep_token_box": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "tokenizer_class": "LayoutLMv3Tokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0703636b3e2a82e4574362732b505264a6fa78383475ce61021927f8f3ebb7d8
+size 4792