{
    "type": "residual_transformer",
    "n_obs_steps": 1,
    "normalization_mapping": {
        "VISUAL": "MEAN_STD",
        "STATE": "MEAN_STD",
        "ACTION": "MEAN_STD",
        "ENV": "MEAN_STD",
        "CONTEXT": "MEAN_STD"
    },
    "input_features": {
        "observation.images.image": {
            "type": "VISUAL",
            "shape": [
                3,
                256,
                256
            ]
        },
        "observation.images.wrist_image": {
            "type": "VISUAL",
            "shape": [
                3,
                256,
                256
            ]
        },
        "observation.state": {
            "type": "STATE",
            "shape": [
                8
            ]
        },
        "vlm_hidden": {
            "type": "CONTEXT",
            "shape": [
                960
            ]
        }
    },
    "output_features": {
        "action": {
            "type": "ACTION",
            "shape": [
                7
            ]
        }
    },
    "device": "cuda",
    "use_amp": false,
    "push_to_hub": true,
    "repo_id": "rt_libero_object_action",
    "private": null,
    "tags": null,
    "license": null,
    "vision_backbone": "resnet18",
    "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
    "freeze_vision_backbone": false,
    "replace_final_stride_with_dilation": false,
    "dim_model": 512,
    "n_heads": 8,
    "n_encoder_layers": 6,
    "dim_feedforward": 2048,
    "dropout": 0.1,
    "optimizer_lr": 1e-05,
    "optimizer_weight_decay": 1e-05
}