config.json

{
  "arch_specifier": "no-align+fused-gelu-mlp",
  "architectures": [
    "OpenVLAForActionPrediction"
  ],
  "auto_map": {
    "AutoConfig": "configuration_prismatic.OpenVLAConfig",
    "AutoModelForVision2Seq": "modeling_prismatic.OpenVLAForActionPrediction"
  },
  "hf_llm_id": "meta-llama/Llama-2-7b-hf",
  "image_resize_strategy": "resize-naive",
  "image_sizes": [
    224,
    224
  ],
  "llm_backbone_id": "llama2-7b-pure",
  "llm_max_length": 2048,
  "model_type": "openvla",
  "n_action_bins": 256,
  "norm_stats": {
    "bridge_dataset": {
      "action": {
        "mask": [
          true,
          true,
          true,
          true,
          true,
          true,
          false
        ],
        "max": [
          0.41691166162490845,
          0.25864794850349426,
          0.21218234300613403,
          3.122201919555664,
          1.8618112802505493,
          6.280478477478027,
          1.0
        ],
        "mean": [
          0.00023341824999079108,
          0.0001300419680774212,
          -0.0001276263501495123,
          -0.0001556589122628793,
          -0.00040393511881120503,
          0.0002355832839384675,
          0.5764582753181458
        ],
        "min": [
          -0.4007510244846344,
          -0.13874775171279907,
          -0.22553899884223938,
          -3.2010786533355713,
          -1.8618112802505493,
          -6.279075622558594,
          0.0
        ],
        "q01": [
          -0.02872725307941437,
          -0.04170349963009357,
          -0.026093858778476715,
          -0.08092105075716972,
          -0.09288699507713317,
          -0.20718276381492615,
          0.0
        ],
        "q99": [
          0.028309678435325586,
          0.040855254605412394,
          0.040161586627364146,
          0.08192047759890528,
          0.07792850524187081,
          0.20382574498653397,
          1.0
        ],
        "std": [
          0.009765730239450932,
          0.013689522631466389,
          0.012667152099311352,
          0.028534481301903725,
          0.030637893825769424,
          0.07691768556833267,
          0.49736595153808594
        ]
      },
      "num_trajectories": 60064,
      "num_transitions": 2135463,
      "proprio": {
        "max": [
          0.0,
          0.0,
          0.0,
          0.0,
          0.0,
          0.0,
          0.0
        ],
        "mean": [
          0.0,
          0.0,
          0.0,
          0.0,
          0.0,
          0.0,
          0.0
        ],
        "min": [
          0.0,
          0.0,
          0.0,
          0.0,
          0.0,
          0.0,
          0.0
        ],
        "q01": [
          0.0,
          0.0,
          0.0,
          0.0,
          0.0,
          0.0,
          0.0
        ],
        "q99": [
          0.0,
          0.0,
          0.0,
          0.0,
          0.0,
          0.0,
          0.0
        ],
        "std": [
          0.0,
          0.0,
          0.0,
          0.0,
          0.0,
          0.0,
          0.0
        ]
      }
    }
  },
  "output_projector_states": false,
  "pad_to_multiple_of": 64,
  "pad_token_id": 32000,
  "text_config": {
    "model_type": "llama",
    "pad_token_id": 32000,
    "torch_dtype": "bfloat16",
    "vocab_size": 32064
  },
  "timm_model_ids": [
    "vit_large_patch14_reg4_dinov2.lvd142m",
    "vit_so400m_patch14_siglip_224"
  ],
  "timm_override_act_layers": [
    null,
    null
  ],
  "torch_dtype": "bfloat16",
  "transformers_version": "4.40.1",
  "use_fused_vision_backbone": true,
  "vision_backbone_id": "dinosiglip-vit-so-224px"
}