config.json

{
  "architectures": [
    "Sapiens2Model"
  ],
  "attention_dropout": 0.0,
  "drop_path_rate": 0.0,
  "flip_pairs": null,
  "head_config": null,
  "hidden_act": "silu",
  "hidden_size": 1280,
  "image_size": [
    1024,
    768
  ],
  "initializer_range": 0.02,
  "intermediate_size": 5120,
  "key_bias": true,
  "layerscale_value": 1.0,
  "mlp_bias": true,
  "model_type": "sapiens2",
  "normalize_backbone_outputs": true,
  "num_attention_heads": 16,
  "num_channels": 3,
  "num_first_full_attention_layers": 8,
  "num_hidden_layers": 32,
  "num_key_value_attention_heads": 8,
  "num_key_value_heads_per_layer": [
    16,
    16,
    16,
    16,
    16,
    16,
    16,
    16,
    8,
    8,
    8,
    8,
    8,
    8,
    8,
    8,
    8,
    8,
    8,
    8,
    8,
    8,
    8,
    8,
    16,
    16,
    16,
    16,
    16,
    16,
    16,
    16
  ],
  "num_last_full_attention_layers": 8,
  "num_register_tokens": 8,
  "out_features": [
    "stage32"
  ],
  "out_indices": [
    32
  ],
  "patch_size": 16,
  "pos_embed_jitter": null,
  "pos_embed_rescale": 2.0,
  "pos_embed_shift": null,
  "proj_bias": true,
  "query_bias": true,
  "reshape_hidden_states": true,
  "rms_norm_eps": 1e-06,
  "rope_theta": 100.0,
  "semantic_loss_ignore_index": 255,
  "stage_names": [
    "stem",
    "stage1",
    "stage2",
    "stage3",
    "stage4",
    "stage5",
    "stage6",
    "stage7",
    "stage8",
    "stage9",
    "stage10",
    "stage11",
    "stage12",
    "stage13",
    "stage14",
    "stage15",
    "stage16",
    "stage17",
    "stage18",
    "stage19",
    "stage20",
    "stage21",
    "stage22",
    "stage23",
    "stage24",
    "stage25",
    "stage26",
    "stage27",
    "stage28",
    "stage29",
    "stage30",
    "stage31",
    "stage32"
  ],
  "transformers_version": "5.10.0.dev0",
  "use_gated_mlp": true,
  "use_mask_token": false,
  "use_qk_norm": true,
  "value_bias": true
}