train/models/vilt/base_config.json

{
  "emb_size": 768,
  "feedforward_size": 3072,
  "hidden_size": 768,
  "hidden_act": "gelu",
  "heads_num": 12,
  "layers_num": 12,
  "max_seq_length": 512,
  "dropout": 0.1,
  "data_processor": "vilt",
  "embedding": ["word_patch", "pos", "seg"],
  "encoder": "transformer",
  "mask": "fully_visible",
  "target": ["mlm", "sp"],
  "image_height": 256,
  "image_width": 256,
  "patch_size": 32
}