{
  "_name_or_path": "xvla",
  "model_type": "xvla",
  "architectures": [
    "XVLA"
  ],
  "auto_map": {
    "AutoConfig": "configuration_xvla.XVLAConfig",
    "AutoModel": "modeling_xvla.XVLA"
  },
  "action_mode": "ee6d",
  "use_proprio": true,
  "num_actions": 30,
  "hidden_size": 1024,
  "depth": 24,
  "num_heads": 16,
  "mlp_ratio": 4.0,
  "num_domains": 30,
  "len_soft_prompts": 32,
  "dim_time": 32,
  "max_len_seq": 512,
  "use_hetero_proj": false,
  "soft_prompt_length": 32,
  "florence_config": {
    "model_type": "florence2",
    "bos_token_id": 0,
    "eos_token_id": 2,
    "ignore_index": -100,
    "pad_token_id": 1,
    "projection_dim": 1024,
    "text_config": {
      "vocab_size": 51289,
      "activation_dropout": 0.1,
      "activation_function": "gelu",
      "add_bias_logits": false,
      "add_final_layer_norm": false,
      "attention_dropout": 0.1,
      "bos_token_id": 0,
      "classif_dropout": 0.1,
      "classifier_dropout": 0.0,
      "d_model": 1024,
      "decoder_attention_heads": 16,
      "decoder_ffn_dim": 4096,
      "decoder_layerdrop": 0.0,
      "decoder_layers": 12,
      "decoder_start_token_id": 2,
      "dropout": 0.1,
      "early_stopping": true,
      "encoder_attention_heads": 16,
      "encoder_ffn_dim": 4096,
      "encoder_layerdrop": 0.0,
      "encoder_layers": 12,
      "eos_token_id": 2,
      "forced_eos_token_id": 2,
      "forced_bos_token_id": 0,
      "gradient_checkpointing": false,
      "init_std": 0.02,
      "is_encoder_decoder": true,
      "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1,
        "LABEL_2": 2
      },
      "max_position_embeddings": 4096,
      "no_repeat_ngram_size": 3,
      "normalize_before": false,
      "num_hidden_layers": 12,
      "pad_token_id": 1,
      "scale_embedding": false,
      "num_beams": 3
    },
    "vision_config": {
      "model_type": "davit",
      "drop_path_rate": 0.1,
      "patch_size": [
        7,
        3,
        3,
        3
      ],
      "patch_stride": [
        4,
        2,
        2,
        2
      ],
      "patch_padding": [
        3,
        1,
        1,
        1
      ],
      "patch_prenorm": [
        false,
        true,
        true,
        true
      ],
      "enable_checkpoint": false,
      "dim_embed": [
        256,
        512,
        1024,
        2048
      ],
      "num_heads": [
        8,
        16,
        32,
        64
      ],
      "num_groups": [
        8,
        16,
        32,
        64
      ],
      "depths": [
        1,
        1,
        9,
        1
      ],
      "window_size": 12,
      "projection_dim": 1024,
      "visual_temporal_embedding": {
        "type": "COSINE",
        "max_temporal_embeddings": 100
      },
      "image_pos_embed": {
        "type": "learned_abs_2d",
        "max_pos_embeddings": 50
      },
      "image_feature_source": [
        "spatial_avg_pool",
        "temporal_avg_pool"
      ]
    },
    "vocab_size": 51289,
    "torch_dtype": "float32",
    "is_encoder_decoder": true
  },
  "geometry_conditioning": {
    "enabled": true,
    "da3_source": "da3_encoder_inline",
    "da3_model_name": "depth-anything/DA3-BASE",
    "da3_use_bf16": true,
    "da3_gradient_checkpointing": true,
    "da3_feature_size": 64,
    "da3_feature_layer": "last",
    "da3_process_res": 504,
    "freeze_da3": true,
    "da3_input_dim": 768,
    "use_da3_latent_segmentation": false,
    "segmentation_mode": "none",
    "object_mask_root": null,
    "object_mask_source": "precomputed",
    "allow_missing_masks": true,
    "num_geometry_tokens": 160,
    "fusion_type": "cross_attention",
    "fusion_position": "before_policy",
    "cross_attention_layers": 6,
    "cross_attention_heads": 8,
    "background_weight": 0.2,
    "mask_reduce": "max",
    "geometry_resampler_type": "perceiver",
    "geometry_projector_type": "mlp",
    "debug_shapes": false
  },
  "finetune": {
    "train_backbone": true,
    "train_soft_prompts": true,
    "train_action_head": true,
    "train_geometry_modules": true,
    "train_last_n_policy_layers": -1
  }
}