{
  "schema_version": "robotics_vla_encoder_policy_v1",
  "model_type": "dinov2_small_text_proprio_bc",
  "encoder_id": "facebook/dinov2-small",
  "encoder_config": {
    "return_dict": true,
    "output_hidden_states": false,
    "dtype": "float32",
    "chunk_size_feed_forward": 0,
    "is_encoder_decoder": false,
    "architectures": [
      "Dinov2Model"
    ],
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "problem_type": null,
    "_name_or_path": "",
    "transformers_version": "5.3.0",
    "model_type": "dinov2",
    "hidden_size": 384,
    "num_hidden_layers": 12,
    "num_attention_heads": 6,
    "mlp_ratio": 4,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.0,
    "attention_probs_dropout_prob": 0.0,
    "initializer_range": 0.02,
    "layer_norm_eps": 1e-06,
    "image_size": 518,
    "patch_size": 14,
    "num_channels": 3,
    "qkv_bias": true,
    "layerscale_value": 1.0,
    "drop_path_rate": 0.0,
    "use_swiglu_ffn": false,
    "stage_names": [
      "stem",
      "stage1",
      "stage2",
      "stage3",
      "stage4",
      "stage5",
      "stage6",
      "stage7",
      "stage8",
      "stage9",
      "stage10",
      "stage11",
      "stage12"
    ],
    "apply_layernorm": true,
    "reshape_hidden_states": true,
    "use_mask_token": true,
    "output_attentions": false,
    "out_features": [
      "stage12"
    ],
    "out_indices": [
      12
    ]
  },
  "text_dim": 256,
  "proprio_dim": 32,
  "action_dim": 7,
  "image_size": [
    224,
    224
  ],
  "vision_dim": 384,
  "modality_emb_dim": 256,
  "parameter_count": 24434823,
  "freeze_encoder": true,
  "adapter_inputs": [
    "image",
    "proprio",
    "instruction",
    "task",
    "difficulty",
    "step",
    "horizon"
  ],
  "forbidden_adapter_inputs": [
    "raw_obs",
    "object_state",
    "sim_state",
    "mujoco_data"
  ],
  "training_data": "hf:random-sequence/flock-robotics-vla-training-v2",
  "run_tag": "dino_v13_unfreeze"
}