Dumping raw files

.gitattributes

@@ -0,0 +1 @@
+*.bin filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,131 @@
+{
+  "EE_config": {
+    "apply_ocr": true,
+    "batch_size": 2,
+    "checkpoint": "",
+    "data_parallel": false,
+    "dataset": "jordyvl/rvl_cdip_easyocr",
+    "device": "cuda",
+    "downsampling": 0,
+    "epochs": 5,
+    "eval_batch_size": 1,
+    "eval_start": false,
+    "exit_threshold": -1,
+    "forward_signature": [
+      "input_ids",
+      "attention_mask",
+      "bbox",
+      "pixel_values",
+      "labels",
+      "token_type_ids",
+      "position_ids",
+      "head_mask",
+      "inputs_embeds",
+      "output_attentions",
+      "output_hidden_states",
+      "return_dict",
+      "kwargs"
+    ],
+    "get_raw_ocr_data": true,
+    "global_threshold": 1.000001,
+    "gradient_accumulation_steps": 32,
+    "lowercase": false,
+    "lr": 2e-05,
+    "model": "EElayoutlmv3",
+    "model_weights": "microsoft/layoutlmv3-base",
+    "optimizer": "AdamW",
+    "seed": 42,
+    "test_dataset": "jordyvl/rvl_cdip_100_examples_per_class",
+    "use_images": true,
+    "warmup_ratio": 0,
+    "weight_decay": 0
+  },
+  "_name_or_path": "microsoft/layoutlmv3-base",
+  "architectures": [
+    "LayoutLMv3EEForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "coordinate_size": 128,
+  "eos_token_id": 2,
+  "exit_config": {
+    "encoder_layer_strategy": "ramp",
+    "exit_head_num_layers": 2,
+    "exits": [
+      "text_avg",
+      "vision_avg",
+      1,
+      4,
+      8
+    ],
+    "global_threshold": 1.000001,
+    "inference_strategy": "max_confidence",
+    "training_strategy": "joint_weighted_avg"
+  },
+  "has_relative_attention_bias": true,
+  "has_spatial_attention_bias": true,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "letter",
+    "1": "form",
+    "2": "email",
+    "3": "handwritten",
+    "4": "advertisement",
+    "5": "scientific_report",
+    "6": "scientific_publication",
+    "7": "specification",
+    "8": "file_folder",
+    "9": "news_article",
+    "10": "budget",
+    "11": "invoice",
+    "12": "presentation",
+    "13": "questionnaire",
+    "14": "resume",
+    "15": "memo"
+  },
+  "initializer_range": 0.02,
+  "input_size": 224,
+  "intermediate_size": 3072,
+  "label2id": {
+    "advertisement": 4,
+    "budget": 10,
+    "email": 2,
+    "file_folder": 8,
+    "form": 1,
+    "handwritten": 3,
+    "invoice": 11,
+    "letter": 0,
+    "memo": 15,
+    "news_article": 9,
+    "presentation": 12,
+    "questionnaire": 13,
+    "resume": 14,
+    "scientific_publication": 6,
+    "scientific_report": 5,
+    "specification": 7
+  },
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "type_vocab_size": 1,
+  "visual_embed": true,
+  "vocab_size": 50265
+}

preprocessor_config.json

@@ -0,0 +1,19 @@
+{
+  "apply_ocr": false,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "LayoutLMv3FeatureExtractor",
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "ocr_lang": null,
+  "resample": 2,
+  "size": 224
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4289a1b57786472b5bcf7b9fa225817ba154fb79b7c9efd79e77b1026d554745
+size 515863297

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,85 @@
+{
+  "add_prefix_space": true,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token_box": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "name_or_path": "microsoft/layoutlmv3-base",
+  "only_label_first_subword": true,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token_box": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "pad_token_label": -100,
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token_box": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "special_tokens_map_file": null,
+  "tokenizer_class": "LayoutLMv3Tokenizer",
+  "trim_offsets": true,
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2945bb49adc620e1c4a2551bfd3f0f53137be279823629e361c541cbf7f812aa
+size 3579