config.json

{
  "_name_or_path": "microsoft/layoutlmv3-base",
  "architectures": [
    "LayoutLMv3ForSequenceClassification"
  ],
  "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": "Phi\u1ebfu k\u1ebft qu\u1ea3",
    "1": "Bi\u00ean b\u1ea3n h\u1ed9i ch\u1ea9n",
    "2": "B\u1ec7nh \u00e1n",
    "3": "B\u1ea3ng k\u00ea",
    "4": "Gi\u1ea5y ch\u1ee9ng nh\u1eadn ph\u1eabu thu\u1eadt",
    "5": "Gi\u1ea5y ra vi\u1ec7n",
    "6": "Phi\u1ebfu ch\u1ec9 \u0111\u1ecbnh",
    "7": "\u0110\u01a1n thu\u1ed1c",
    "8": "Phi\u1ebfu kh\u00e1m",
    "9": "T\u1edd \u0111i\u1ec1u tr\u1ecb"
  },
  "initializer_range": 0.02,
  "input_size": 224,
  "intermediate_size": 3072,
  "label2id": {
    "Bi\u00ean b\u1ea3n h\u1ed9i ch\u1ea9n": 1,
    "B\u1ea3ng k\u00ea": 3,
    "B\u1ec7nh \u00e1n": 2,
    "Gi\u1ea5y ch\u1ee9ng nh\u1eadn ph\u1eabu thu\u1eadt": 4,
    "Gi\u1ea5y ra vi\u1ec7n": 5,
    "Phi\u1ebfu ch\u1ec9 \u0111\u1ecbnh": 6,
    "Phi\u1ebfu kh\u00e1m": 8,
    "Phi\u1ebfu k\u1ebft qu\u1ea3": 0,
    "T\u1edd \u0111i\u1ec1u tr\u1ecb": 9,
    "\u0110\u01a1n thu\u1ed1c": 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": "4.27.2",
  "type_vocab_size": 1,
  "visual_embed": true,
  "vocab_size": 50265
}