config.json

{
  "converter_version": 1,
  "model_id": "robbyant/lingbot-depth-pretrain-vitl-14-v0.5",
  "num_tokens_range": [
    1200,
    3600
  ],
  "patch_size": 14,
  "num_heads": 16,
  "embed_dim": 1024,
  "depth": 24,
  "remap_depth_in": "log",
  "remap_depth_out": "linear",
  "image_mean": [
    0.48500001430511475,
    0.4560000002384186,
    0.4059999883174896
  ],
  "image_std": [
    0.2290000021457672,
    0.2240000069141388,
    0.22499999403953552
  ],
  "neck": 1024
}