OCR-LayoutLMv3 / config.json
jinhybr's picture
Training in progress, step 500
f494dfb
{
"_name_or_path": "microsoft/layoutlmv3-base",
"architectures": [
"LayoutLMv3ForTokenClassification"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": 0,
"classifier_dropout": null,
"coordinate_size": 128,
"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-HEADER",
"2": "I-HEADER",
"3": "B-QUESTION",
"4": "I-QUESTION",
"5": "B-ANSWER",
"6": "I-ANSWER"
},
"initializer_range": 0.02,
"input_size": 224,
"intermediate_size": 3072,
"label2id": {
"B-ANSWER": 5,
"B-HEADER": 1,
"B-QUESTION": 3,
"I-ANSWER": 6,
"I-HEADER": 2,
"I-QUESTION": 4,
"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,
"torch_dtype": "float32",
"transformers_version": "4.25.0.dev0",
"type_vocab_size": 1,
"visual_embed": true,
"vocab_size": 50265
}