|
{ |
|
"_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_object": { |
|
"action": { |
|
"mean": [ |
|
0.07096529006958008, |
|
0.13498851656913757, |
|
-0.04601382836699486, |
|
0.00123520044144243, |
|
0.006998839322477579, |
|
-0.015027612447738647, |
|
0.46428999304771423 |
|
], |
|
"std": [ |
|
0.2681235373020172, |
|
0.43846824765205383, |
|
0.4474974274635315, |
|
0.024446550756692886, |
|
0.049355510622262955, |
|
0.042107198387384415, |
|
0.49879148602485657 |
|
], |
|
"max": [ |
|
0.9375, |
|
0.8919642567634583, |
|
0.9375, |
|
0.17678570747375488, |
|
0.35035714507102966, |
|
0.1810714304447174, |
|
1.0 |
|
], |
|
"min": [ |
|
-0.8839285969734192, |
|
-0.9375, |
|
-0.9375, |
|
-0.15000000596046448, |
|
-0.29035714268684387, |
|
-0.32892856001853943, |
|
0.0 |
|
], |
|
"q01": [ |
|
-0.5383928418159485, |
|
-0.8758928775787354, |
|
-0.9375, |
|
-0.06964285671710968, |
|
-0.11678571254014969, |
|
-0.15964286029338837, |
|
0.0 |
|
], |
|
"q99": [ |
|
0.8464285731315613, |
|
0.84375, |
|
0.9375, |
|
0.08142857253551483, |
|
0.14892856776714325, |
|
0.0867857113480568, |
|
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": 66984, |
|
"num_trajectories": 454 |
|
} |
|
}, |
|
"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" |
|
} |
|
|