{ "arch_specifier": "no-align+gelu-mlp", "architectures": [ "OpenVLAForActionPrediction" ], "auto_map": { "AutoConfig": "configuration_prismatic.OpenVLAConfig", "AutoModelForVision2Seq": "modeling_prismatic.OpenVLAForActionPrediction" }, "hf_llm_id": "lmsys/vicuna-7b-v1.5", "image_resize_strategy": "letterbox", "image_sizes": [ 224 ], "llm_backbone_id": "vicuna-v15-7b", "llm_max_length": 2048, "model_type": "openvla", "n_action_bins": 256, "norm_stats": { "bridge_orig": { "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": [ 0.00023341893393080682, 0.0001300494186580181, -0.0001276240509469062, -0.00015565630747005343, -0.0004039352061226964, 0.00023557755048386753, 0.5764579772949219 ], "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": [ 0.009765958413481712, 0.01368918176740408, 0.012667348608374596, 0.02853415347635746, 0.03063797391951084, 0.07691441476345062, 0.4973689615726471 ] }, "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_so400m_patch14_siglip_224" ], "timm_override_act_layers": [ null ], "torch_dtype": "bfloat16", "transformers_version": "4.40.1", "use_fused_vision_backbone": false, "vision_backbone_id": "siglip-vit-so400m" }