config.json

{
  "act_adaptor": "mlp3x_silu",
  "act_pos_emb_config": [
    [
      "action",
      24
    ],
    [
      "register",
      4
    ]
  ],
  "action_dim": 20,
  "img_pos_emb_config": null,
  "img_token_dim": 2176,
  "lang_pos_emb_config": null,
  "lang_token_dim": null,
  "max_img_len": null,
  "max_lang_len": null,
  "noise_scheduler": {
    "num_inference_timesteps": 5
  },
  "pred_horizon": 24,
  "rdt": {
    "depth": 14,
    "ffn_dim_multiplier": null,
    "hidden_size": 1024,
    "multiple_of": 256,
    "norm_eps": 1e-05,
    "num_heads": 8,
    "num_kv_heads": 4,
    "num_register_tokens": 4,
    "use_flash_attn": true
  },
  "selected_layers": [
    0,
    1,
    2,
    3,
    4,
    5,
    6,
    7,
    8,
    9,
    10,
    11,
    12,
    13
  ],
  "state_adaptor": "mlp3x_silu",
  "state_dim": 20
}