{ | |
"arch_specifier": "no-align+fused-gelu-mlp", | |
"architectures": [ | |
"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_oxe": { | |
"action": { | |
"mask": [ | |
true, | |
true, | |
true, | |
true, | |
true, | |
true, | |
false | |
], | |
"max": [ | |
0.06491869688034058, | |
0.10465731471776962, | |
0.07840253412723541, | |
0.48420292139053345, | |
0.638953685760498, | |
6.272472858428955, | |
1.0 | |
], | |
"mean": [ | |
0.00028933861176483333, | |
0.00014495271898340434, | |
-0.0002190050290664658, | |
-0.00030238323961384594, | |
-0.00065906613599509, | |
0.00026461915695108473, | |
0.6497402787208557 | |
], | |
"min": [ | |
-0.0840979814529419, | |
-0.13874775171279907, | |
-0.06363017857074738, | |
-0.7343192100524902, | |
-0.35826510190963745, | |
-6.274418830871582, | |
0.0 | |
], | |
"q01": [ | |
-0.028917968273162842, | |
-0.04320061206817627, | |
-0.02554995596408844, | |
-0.08335682392120361, | |
-0.10034397959709168, | |
-0.15845893859863283, | |
0.0 | |
], | |
"q99": [ | |
0.0288640558719635, | |
0.04256527900695803, | |
0.042192451655864716, | |
0.08410081028938296, | |
0.08085504114627841, | |
0.1651961439847947, | |
1.0 | |
], | |
"std": [ | |
0.01000096183270216, | |
0.014115503057837486, | |
0.013139418326318264, | |
0.029833171516656876, | |
0.0330631285905838, | |
0.0608142726123333, | |
0.47789132595062256 | |
] | |
}, | |
"num_trajectories": 28935, | |
"num_transitions": 925025, | |
"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" | |
} | |