| { | |
| "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": { | |
| "libero_spatial_no_noops": { | |
| "action": { | |
| "mask": [ | |
| true, | |
| true, | |
| true, | |
| true, | |
| true, | |
| true, | |
| false | |
| ], | |
| "max": [ | |
| 0.9375, | |
| 0.9375, | |
| 0.9375, | |
| 0.1971428543329239, | |
| 0.33642858266830444, | |
| 0.375, | |
| 1.0 | |
| ], | |
| "mean": [ | |
| 0.15312479436397552, | |
| 0.13707277178764343, | |
| -0.15526802837848663, | |
| -0.005176450591534376, | |
| -0.01120874285697937, | |
| -0.020194264128804207, | |
| 0.4578818082809448 | |
| ], | |
| "min": [ | |
| -0.9375, | |
| -0.9375, | |
| -0.9375, | |
| -0.1875, | |
| -0.3675000071525574, | |
| -0.36000001430511475, | |
| 0.0 | |
| ], | |
| "q01": [ | |
| -0.7454732114076613, | |
| -0.6616071462631226, | |
| -0.9375, | |
| -0.1071428582072258, | |
| -0.20678570866584778, | |
| -0.1842857152223587, | |
| 0.0 | |
| ], | |
| "q99": [ | |
| 0.9375, | |
| 0.8758928775787354, | |
| 0.9321428537368774, | |
| 0.1039285734295845, | |
| 0.17678570747375488, | |
| 0.14571428298950195, | |
| 1.0 | |
| ], | |
| "std": [ | |
| 0.41272708773612976, | |
| 0.34724321961402893, | |
| 0.50869220495224, | |
| 0.037266165018081665, | |
| 0.07244449853897095, | |
| 0.05762382969260216, | |
| 0.49827873706817627 | |
| ] | |
| }, | |
| "num_trajectories": 432, | |
| "num_transitions": 52970, | |
| "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" | |
| } | |