{
    "type": "longwam",
    "n_obs_steps": 1,
    "input_features": {
        "observation.images.image": {
            "type": "VISUAL",
            "shape": [
                3,
                224,
                224
            ]
        },
        "observation.images.image2": {
            "type": "VISUAL",
            "shape": [
                3,
                224,
                224
            ]
        },
        "observation.state": {
            "type": "STATE",
            "shape": [
                8
            ]
        }
    },
    "output_features": {
        "action": {
            "type": "ACTION",
            "shape": [
                7
            ]
        }
    },
    "device": "cpu",
    "dtype": "bfloat16",
    "use_amp": false,
    "use_peft": false,
    "push_to_hub": false,
    "repo_id": null,
    "private": null,
    "tags": null,
    "license": null,
    "pretrained_path": null,
    "pretrained_revision": null,
    "past_obs_steps": 48,
    "video_stride": 4,
    "future_video_steps": 32,
    "action_horizon": 32,
    "inference_action_horizon": 80,
    "n_action_steps": 10,
    "denoising": "idm",
    "num_inference_steps": 10,
    "imagine_sigma": 0.9,
    "imagine_steps": 4,
    "flow_shift": 5.0,
    "inference_seed": 1,
    "camera_keys": [
        "observation.images.image",
        "observation.images.image2"
    ],
    "camera_size": [
        224,
        224
    ],
    "action_dim": 7,
    "proprio_dim": 8,
    "tokenizer_name": "google/umt5-xxl",
    "tokenizer_max_length": 128,
    "prompt_template": "A video recorded from a robot's point of view executing the following instruction: {task}",
    "video_config": {
        "added_kv_proj_dim": null,
        "attention_head_dim": 128,
        "cross_attn_norm": true,
        "eps": 1e-06,
        "ffn_dim": 14336,
        "freq_dim": 256,
        "image_dim": null,
        "in_channels": 48,
        "num_attention_heads": 24,
        "num_layers": 30,
        "out_channels": 48,
        "patch_size": [
            1,
            2,
            2
        ],
        "pos_embed_seq_len": null,
        "qk_norm": "rms_norm_across_heads",
        "rope_max_seq_len": 1024,
        "text_dim": 4096
    },
    "vae_config": {
        "attn_scales": [],
        "base_dim": 160,
        "decoder_base_dim": 256,
        "dim_mult": [
            1,
            2,
            4,
            4
        ],
        "dropout": 0.0,
        "in_channels": 12,
        "is_residual": true,
        "latents_mean": [
            -0.2289,
            -0.0052,
            -0.1323,
            -0.2339,
            -0.2799,
            0.0174,
            0.1838,
            0.1557,
            -0.1382,
            0.0542,
            0.2813,
            0.0891,
            0.157,
            -0.0098,
            0.0375,
            -0.1825,
            -0.2246,
            -0.1207,
            -0.0698,
            0.5109,
            0.2665,
            -0.2108,
            -0.2158,
            0.2502,
            -0.2055,
            -0.0322,
            0.1109,
            0.1567,
            -0.0729,
            0.0899,
            -0.2799,
            -0.123,
            -0.0313,
            -0.1649,
            0.0117,
            0.0723,
            -0.2839,
            -0.2083,
            -0.052,
            0.3748,
            0.0152,
            0.1957,
            0.1433,
            -0.2944,
            0.3573,
            -0.0548,
            -0.1681,
            -0.0667
        ],
        "latents_std": [
            0.4765,
            1.0364,
            0.4514,
            1.1677,
            0.5313,
            0.499,
            0.4818,
            0.5013,
            0.8158,
            1.0344,
            0.5894,
            1.0901,
            0.6885,
            0.6165,
            0.8454,
            0.4978,
            0.5759,
            0.3523,
            0.7135,
            0.6804,
            0.5833,
            1.4146,
            0.8986,
            0.5659,
            0.7069,
            0.5338,
            0.4889,
            0.4917,
            0.4069,
            0.4999,
            0.6866,
            0.4093,
            0.5709,
            0.6065,
            0.6415,
            0.4944,
            0.5726,
            1.2042,
            0.5458,
            1.6887,
            0.3971,
            1.06,
            0.3943,
            0.5537,
            0.5444,
            0.4089,
            0.7468,
            0.7744
        ],
        "num_res_blocks": 2,
        "out_channels": 12,
        "patch_size": 2,
        "scale_factor_spatial": 16,
        "scale_factor_temporal": 4,
        "temperal_downsample": [
            false,
            true,
            true
        ],
        "z_dim": 48
    },
    "text_encoder_config": {
        "architectures": [
            "UMT5EncoderModel"
        ],
        "classifier_dropout": 0.0,
        "d_ff": 10240,
        "d_kv": 64,
        "d_model": 4096,
        "decoder_start_token_id": 0,
        "dense_act_fn": "gelu_new",
        "dropout_rate": 0.1,
        "eos_token_id": 1,
        "feed_forward_proj": "gated-gelu",
        "initializer_factor": 1.0,
        "is_encoder_decoder": true,
        "is_gated_act": true,
        "layer_norm_epsilon": 1e-06,
        "model_type": "umt5",
        "num_decoder_layers": 24,
        "num_heads": 64,
        "num_layers": 24,
        "output_past": true,
        "pad_token_id": 0,
        "relative_attention_max_distance": 128,
        "relative_attention_num_buckets": 32,
        "scalable_attention": true,
        "tie_word_embeddings": false,
        "tokenizer_class": "T5Tokenizer",
        "torch_dtype": "bfloat16",
        "transformers_version": "4.48.0.dev0",
        "use_cache": true,
        "vocab_size": 256384
    },
    "action_hidden_dim": 1024,
    "action_ffn_dim": 4096,
    "use_gradient_checkpointing": false,
    "toggle_action_dimensions": [
        -1
    ],
    "optimizer_lr": 0.0001,
    "optimizer_weight_decay": 0.01,
    "optimizer_betas": [
        0.9,
        0.95
    ],
    "loss_lambda_video": 1.0,
    "loss_lambda_action": 1.0,
    "normalization_mapping": {
        "VISUAL": "IDENTITY",
        "STATE": "MIN_MAX",
        "ACTION": "MIN_MAX"
    }
}