config.json

{
  "_name_or_path": "openvla/openvla-7b",
  "arch_specifier": "no-align+fused-gelu-mlp",
  "architectures": [
    "OpenVLAForActionPrediction"
  ],
  "auto_map": {
    "AutoConfig": "openvla/openvla-7b--configuration_prismatic.OpenVLAConfig",
    "AutoModelForVision2Seq": "openvla/openvla-7b--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": {
    "libero_goal": {
      "action": {
        "mean": [
          0.04721052572131157,
          0.028835246339440346,
          -0.1485840231180191,
          -0.0025010062381625175,
          0.026408178731799126,
          0.027379808947443962,
          0.6299911737442017
        ],
        "std": [
          0.3968801498413086,
          0.3473387360572815,
          0.49239858984947205,
          0.055331431329250336,
          0.07844757288694382,
          0.10008802264928818,
          0.48270025849342346
        ],
        "max": [
          0.9375,
          0.9375,
          0.9375,
          0.3557142913341522,
          0.375,
          0.375,
          1.0
        ],
        "min": [
          -0.9375,
          -0.9375,
          -0.9375,
          -0.2582142949104309,
          -0.375,
          -0.2871428430080414,
          0.0
        ],
        "q01": [
          -0.8785714507102966,
          -0.7553571462631226,
          -0.9375,
          -0.1510714292526245,
          -0.1639285683631897,
          -0.13777500048279764,
          0.0
        ],
        "q99": [
          0.9375,
          0.9107142686843872,
          0.9375,
          0.20357142388820648,
          0.26357144117355347,
          0.375,
          1.0
        ],
        "mask": [
          true,
          true,
          true,
          true,
          true,
          true,
          false
        ]
      },
      "proprio": {
        "mean": [
          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
        ],
        "max": [
          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
        ]
      },
      "num_transitions": 52042,
      "num_trajectories": 428
    }
  },
  "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"
}