| { |
| "arch_specifier": "no-align+fused-gelu-mlp", |
| "architectures": [ |
| "OpenVLAForActionPrediction" |
| ], |
| "auto_map": { |
| "AutoConfig": "configuration_prismatic.OpenVLAConfig" |
| }, |
| "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": { |
| "fractal20220817_data": { |
| "action": { |
| "mask": [ |
| true, |
| true, |
| true, |
| true, |
| true, |
| true, |
| false |
| ], |
| "max": [ |
| 2.9984593391418457, |
| 22.09052848815918, |
| 2.7507524490356445, |
| 1.570636510848999, |
| 1.5321086645126343, |
| 1.5691522359848022, |
| 1.0 |
| ], |
| "mean": [ |
| 0.006987560540437698, |
| 0.0062659201212227345, |
| -0.012625135481357574, |
| 0.04333367198705673, |
| -0.00575620960444212, |
| 0.0009130347170867026, |
| 0.5354204773902893 |
| ], |
| "min": [ |
| -2.0204520225524902, |
| -5.497899532318115, |
| -2.031663417816162, |
| -1.569917917251587, |
| -1.569892168045044, |
| -1.570419430732727, |
| 0.0 |
| ], |
| "q01": [ |
| -0.22453527510166169, |
| -0.14820013284683228, |
| -0.231589707583189, |
| -0.3517994859814644, |
| -0.4193011274933815, |
| -0.43643461108207704, |
| 0.0 |
| ], |
| "q99": [ |
| 0.17824687153100965, |
| 0.14938379630446405, |
| 0.21842354819178575, |
| 0.5892666035890578, |
| 0.35272657424211445, |
| 0.44796681255102094, |
| 1.0 |
| ], |
| "std": [ |
| 0.06921132653951645, |
| 0.059704605489969254, |
| 0.07353130728006363, |
| 0.1561046838760376, |
| 0.13164442777633667, |
| 0.14593853056430817, |
| 0.497112900018692 |
| ] |
| }, |
| "num_trajectories": 87212, |
| "num_transitions": 3786400, |
| "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": "4.43.3", |
| "use_fused_vision_backbone": true, |
| "vision_backbone_id": "dinosiglip-vit-so-224px" |
| } |
|
|