config.json

{
  "_name_or_path": "vikp/layout6",
  "architectures": [
    "EfficientViTForSemanticSegmentation"
  ],
  "attention_probs_dropout_prob": 0.0,
  "classifier_dropout_prob": 0.0,
  "decoder_hidden_size": 512,
  "decoder_layer_hidden_size": 128,
  "depths": [
    1,
    1,
    1,
    6,
    6
  ],
  "head_dim": 32,
  "hidden_dropout_prob": 0.0,
  "hidden_sizes": [
    32,
    64,
    160,
    256
  ],
  "id2label": {
    "0": "Blank",
    "1": "Caption",
    "2": "Footnote",
    "3": "Formula",
    "4": "List-item",
    "5": "Page-footer",
    "6": "Page-header",
    "7": "Picture",
    "8": "Section-header",
    "9": "Table",
    "10": "Text",
    "11": "Title"
  },
  "initializer_range": 0.02,
  "label2id": {
    "Blank": 0,
    "Caption": 1,
    "Footnote": 2,
    "Formula": 3,
    "List-item": 4,
    "Page-footer": 5,
    "Page-header": 6,
    "Picture": 7,
    "Section-header": 8,
    "Table": 9,
    "Text": 10,
    "Title": 11
  },
  "layer_norm_eps": 1e-06,
  "model_type": "efficientvit",
  "num_channels": 3,
  "num_classes": 2,
  "num_stages": 4,
  "patch_size": [
    7,
    7
  ],
  "semantic_loss_ignore_index": -1,
  "strides": [
    2,
    2,
    2,
    2,
    2
  ],
  "torch_dtype": "float16",
  "transformers_version": "4.41.2",
  "widths": [
    32,
    64,
    128,
    256,
    512
  ]
}