train/models/beit/base_config.json

{
  "emb_size": 768,
  "feedforward_size": 3072,
  "hidden_size": 768,
  "hidden_act": "gelu",
  "heads_num": 12,
  "layers_num": 12,
  "dropout": 0.1,
  "data_processor": "beit",
  "embedding": ["masked_patch", "pos"],
  "encoder": "transformer",
  "mask": "fully_visible",
  "target": ["mlm"],
  "image_height": 256,
  "image_width": 256,
  "patch_size": 16,
  "image_preprocess": ["crop"],
  "tokenizer": "vqgan",
  "image_tokenizer": {
    "is_gumbel": false,
    "is_transformer": false,
    "image_vocab_size": 16384,
    "frame_size": 16
  }
}